Neuron Explorer

Qwen3-0.6B

'and' closing a list of items

A neuron in layer 17 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 joins two or more names or things, like "X and Y" in a list. When it was turned up, the model started stringing together "and and and" over and over.

Written by Claude from this neuron's activations and steering outputs. Confidence: high. 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

    , of which only three have survived: the⏎Auberge de France, the Auberge d'Angleterre and the Auberge de Provence and⏎After the foundation of Valletta in 1566, the

  2. #2 peak

    2008's major hurricanes, Gustav and Ike, as well as other powerful storms, such as 2005's Katrina and Rita and 2004's Ivan.⏎API plays two primary roles for the industry

  3. #3 peak

    well levels of arsenic, cadmium, manganese, and lead and birth defects prevalence. The studies used a statewide database of private well contaminants collected by

  4. #4 peak

    North American) family.⏎Where Do Anchovies Come From?⏎Anchovies are saltwater forage fish, native to the Mediterranean and the Black Sea and thus very popular in the local cuisine.⏎Similar to herring, anchovies run

  5. #5 peak

    iting can refer to criminally duplicating currency, documents such as passports, birth certificates, drivers’ licenses or deeds, or even goods such as clothing or accessories and representing them as being brand name products. Counterfeiting of money is a federal

  6. #6 peak

    name suggests, yellow-brown in colour. In it’s early stages, it is often mistaken for sand or dirt or a stain on the pool sides or floor and unlike green algae though, mustard algae is not slimy.⏎Mustard

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: the idea of a better understanding of the world, which would allow us to better understand ourselves. Then, with that understanding, we would be better able to act, with that insight, we would have a better sense of ourselves. 这

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

    's global environment for promoting peace and non-violence among mankind."<|endoftext|>Processing nodes in a graph one at a time, usually in

  2. #2 peak

    and dimension to an outfit, and can be used to create a sense of contrast or harmony. When choosing textures, it is important to consider the season and occasion, as well as your personal preferences. You can also experiment with layering different textures

  3. #3 peak

    , other sources of individual variation, or environmental conditions.⏎You have requested a machine translation of selected content from our databases. This functionality is provided solely for your convenience and is in no way intended to replace human translation. Neither BioOne nor the owners

  4. #4 peak

    of education, from kindergarten to college and beyond. Sometimes, publishing companies hire curriculum developers when they want to update textbooks. These professionals need excellent research and fact-checking skills, and they should also understand what learners need.⏎3. Product Testing (

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. L10:74 excites
  2. L13:557 suppresses
  3. L16:376 suppresses 'or' joining alternatives
  4. L13:1296 suppresses
  5. L4:57 suppresses
  6. L9:92 suppresses "and" or "or" joining two items
  7. L13:131 excites 'and' joining parallel phrases
  8. L10:1643 suppresses
  9. L16:2432 suppresses
  10. L14:1116 weakly excites 'and' inside lists
  11. L16:1669 weakly excites
  12. L13:1066 weakly excites
  13. L13:1132 weakly excites
  14. L5:1577 weakly suppresses
  15. L11:1005 weakly suppresses
  16. L7:377 weakly excites
  17. L2:2124 weakly suppresses
  18. L13:1081 weakly suppresses
  19. L14:1746 weakly suppresses
  20. L4:62 weakly excites
  21. L16:2996 weakly suppresses
  22. L5:1861 weakly suppresses
  23. L1:1644 weakly suppresses
  24. L16:3017 weakly suppresses

Feeds later layers

  1. L24:205 strongly excites
  2. L26:347 excites the 're' in self-reliant and similar
  3. L19:1245 excites comma opening a list of parallel items
  4. L27:289 excites
  5. L18:1856 suppresses
  6. L25:6 suppresses
  7. L18:1549 suppresses
  8. L26:65 suppresses
  9. L21:739 excites 'both X and Y' pairing words
  10. L22:632 excites
  11. L18:1655 excites 'and' joining two clauses
  12. L23:379 excites
  13. L18:957 excites
  14. L18:870 suppresses
  15. L20:2386 suppresses
  16. L18:1402 excites
  17. L20:1009 excites
  18. L20:75 suppresses
  19. L18:1207 excites
  20. L18:486 suppresses
  21. L21:2699 weakly suppresses
  22. L24:3054 weakly excites
  23. L19:2589 weakly suppresses
  24. L19:3055 weakly excites

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 -6.97 and -6.621 values between -5.92 and -5.561 values between -5.56 and -5.212 values between -5.21 and -4.868 values between -4.86 and -4.512 values between -4.51 and -4.156 values between -3.80 and -3.4511 values between -3.45 and -3.1017 values between -3.10 and -2.748 values between -2.74 and -2.3919 values between -2.39 and -2.0423 values between -2.04 and -1.6924 values between -1.69 and -1.3329 values between -1.33 and -0.9834 values between -0.98 and -0.6356 values between -0.63 and -0.27696 values between -0.27 and 0.082337 values between 0.08 and 0.43564 values between 0.43 and 0.7840 values between 0.78 and 1.145 values between 1.14 and 1.498 values between 1.49 and 1.844 values between 1.84 and 2.194 values between 2.19 and 2.552 values between 2.55 and 2.902 values between 2.90 and 3.251 values between 3.25 and 3.601 values between 3.60 and 3.961 values between 3.96 and 4.311 values between 6.78 and 7.13offnegativepositiveoften

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. and
  2. 和
  3. and
  4. 和技术
  5. 和社会
  6. 性和
  7. và
  8. и
  9. 和完善
  10. 和个人

Suppresses

  1. igor
  2. 溟
  3. obil
  4. ceph
  5. migration
  6. тем
  7. emy
  8. ionales
  9. еш
  10. minate