Neuron Explorer

Qwen3-0.6B

'and' joining two abstract nouns

A neuron in layer 26 of Qwen3-0.6B. Its strongest snippets are very consistent: they mostly peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on the word 'and' when it links two nouns or ideas, such as 'self-awareness and physical understanding' or 'support and motivation'. Turned up, the model repeated words like 'always'; turned down, it repeated 'follow' and 'work'.

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens a prefilled issue on GitHub).

Fires most on

The text windows where this neuron's activation was highest. Amber marks positive activation; the outlined token is the peak. Hover a token for its strength.

  1. #1 peak

    make them citizens of mathematics. Through collegial exchange of free imagination and logical argument, they gain admiration for each other and self-esteem as the harmonious forms they are studying emerge.⏎The class leader simply

  2. #2 peak

    se psychologist and counselors at a group called the Bethesda Counselling Centre are helping Kaswera — and others who lost loved ones to Ebola — to find solace and closure through alternative burial rituals.⏎With a team of four counselors, psychologist Noé

  3. #3 peak

    "In the future, it will no longer be possible to make it through one's entire career just by graduating today. We all need to continually improve our qualifications and learn new things," says

  4. #4 peak

    psychophysical way to learn about ourselves through our personal movement choices. By exploring everyday movements, work and performance with the Alexander Technique, you can increase self-awareness and physical understanding. This understanding can lead to relief from pain, stress and tension,

  5. #5 peak

    , you will be leaving the KidsHealth site.⏎Sickle Cell Disease Association of America⏎This group provides education, advocacy, and other initiatives to promote awareness of and support for sickle cell disease programs.⏎National Institute of Neurological Disorders and Stroke

  6. #6 peak

    ocial therapy or a combination of both for proper treatment of the disorder.<|endoftext|>Goals and resolutions⏎Goals are an essential part of life. They provide us with direction and motivation to work towards something greater than ourselves. Goals give us a sense of purpose

Steering

Push this neuron up or down while the model writes, and watch what changes. The outputs were generated ahead of time, so nothing runs in your browser.

turned down a lot
Prompt

Here is something I have been thinking about lately: follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow follow

Most negative on

Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.

  1. #1 peak

    . There is considerable variation in the canine population regarding the types of responses that are generated by fear-provoking stimuli. Some dogs require a very strong stimulus to elicit fear, while others become extremely anxious in response to mild stimuli or any auditory

  2. #2 peak

    how he prefers to classify recessions.⏎Inherently, what is the main problem with classifying recoveries into alphabet shapes? What sort of complexities does it elide over?⏎Quite simply, if you actually look at the broad measures of aggregate

  3. #3 peak

    OC’s represent a fundamental change in the way students are confronted with material and how they engage in it. The essence of a MOOC is to activate, to elicit interest, action and debate about the content between the students themselves. Short videos

  4. #4 peak

    It also shows, from one lung cancer to another, the cancer stem cells are not the same."⏎Cancer stem cells are a subset of cancer cells believed to elude conventional treatments and eventually regenerate a tumor. Experimentally, they show up as

Connections

Show on map

Which neurons in earlier layers feed this one, and which later ones it feeds. Amber links excite, blue links suppress; longer bars are stronger.

Fed by earlier layers

  1. L24:1080 strongly suppresses
  2. L25:364 strongly suppresses
  3. L24:298 strongly excites 'would' in hypothetical or past statements
  4. L22:627 strongly suppresses
  5. L21:853 strongly excites 'can' after 'and' or a noun subject
  6. L24:314 strongly excites
  7. L19:3044 strongly suppresses
  8. L23:505 strongly suppresses
  9. L21:1708 strongly excites
  10. L21:1657 strongly suppresses
  11. L23:373 strongly suppresses 'to' after a noun or adjective
  12. L20:636 strongly suppresses
  13. L23:257 strongly suppresses
  14. L25:125 suppresses
  15. L25:2260 excites
  16. L25:906 suppresses
  17. L17:1297 excites
  18. L25:418 excites
  19. L25:361 suppresses
  20. L21:322 excites
  21. L25:104 suppresses
  22. L19:858 suppresses
  23. L20:2802 suppresses
  24. L20:349 excites

Feeds later layers

  1. L27:515 strongly suppresses
  2. L27:401 strongly suppresses
  3. L27:247 strongly suppresses
  4. L27:201 strongly suppresses
  5. L27:488 suppresses
  6. L27:880 suppresses
  7. L27:122 suppresses
  8. L27:963 suppresses
  9. L27:577 suppresses
  10. L27:559 suppresses
  11. L27:900 suppresses
  12. L27:645 suppresses
  13. L27:434 suppresses
  14. L27:883 suppresses
  15. L27:801 weakly suppresses
  16. L27:249 weakly excites
  17. L27:520 weakly suppresses
  18. L27:1493 weakly suppresses
  19. L27:1129 weakly suppresses
  20. L27:920 weakly suppresses
  21. L27:1126 weakly suppresses
  22. L27:1059 weakly suppresses
  23. L27:273 weakly suppresses
  24. L27:1283 weakly suppresses

Activation histogram

How often this neuron fires at each strength. Almost always it does close to nothing (the tall bars in the middle); the snippets above are the rare moments it fired hard, amber for positive and blue for negative.

1 values between -32.97 and -31.111 values between -31.11 and -29.261 values between -25.55 and -23.703 values between -23.70 and -21.841 values between -21.84 and -19.996 values between -19.99 and -18.138 values between -18.13 and -16.2814 values between -16.28 and -14.4220 values between -14.42 and -12.5742 values between -12.57 and -10.7139 values between -10.71 and -8.8684 values between -8.86 and -7.00163 values between -7.00 and -5.15302 values between -5.15 and -3.29666 values between -3.29 and -1.441628 values between -1.44 and 0.42585 values between 0.42 and 2.27139 values between 2.27 and 4.1377 values between 4.13 and 5.9840 values between 5.98 and 7.8318 values between 7.83 and 9.6916 values between 9.69 and 11.5414 values between 11.54 and 13.4011 values between 13.40 and 15.257 values between 15.25 and 17.114 values between 17.11 and 18.964 values between 18.96 and 20.821 values between 20.82 and 22.672 values between 22.67 and 24.531 values between 24.53 and 26.382 values between 26.38 and 28.242 values between 28.24 and 30.092 values between 30.09 and 31.953 values between 31.95 and 33.801 values between 39.36 and 41.22offnegativepositiveoften

Logit lens

The words this neuron nudges the model toward (amber) or away from (blue) when it fires. A hint, not a label: many neurons work through later layers instead.

Promotes

  1. eil
  2. 的方向
  3. BOOK
  4. 금
  5. ion
  6. reak
  7. edTextBox
  8. OptionPane
  9. 点了
  10. 子

Suppresses

  1. follow
  2. use
  3. resolve
  4. hold
  5. look
  6. offer
  7. reach
  8. tend
  9. take
  10. carry