Neuron Explorer

Qwen3-0.6B

"as" completing an "as ... as" comparison

A neuron in layer 6 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 "as" in the second half of comparisons like "not as harshly as" or "as well as". It also goes strongly negative on words like "least" and "single" that appear in negated phrases such as "not the least suspicion". Steering did not produce text that clearly follows this pattern.

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

    on the 'wrong' side of the scale. But, in results, the group who had washed their hands was less likely to judge the actions as harshly as the group who had not.⏎In another experiment, a group was asked to read

  2. #2 peak

    of the body, including the brain. As a result, some people may notice that it takes longer to learn new things, they don't remember information as well as they did, or

  3. #3 peak

    a proper breakfast you won’t perform as well mentally – you won’t be as attentive, your memory won’t be as good and you won’t concentrate as well as you could. Children who eat breakfast on a regular basis tend to perform better acad

  4. #4 peak

    00.00. Within four months, these men<|endoftext|>Our discourse by now may have proved to the reader that the⏎British Empire is not as mythical as the propaganda would have us believe.⏎We quote from THE NATIONAL MESSAGE, of London

  5. #5 peak

    may not have the knowledge to present their content with the most efficiency.⏎Bottom line, if you’re not connected to the Internet, you’re not learning as effectively as you could be. Face-to-face interaction is important for students. No one is

  6. #6 peak

    (a new kind of machine-based conflict).⏎The background to Britain’s entry into the war, he states, was not one of weakness, isolation and austerity, as is often argued, but of an abundance of key resources. During the conflict imports

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: in the house of my possession of a house of ground house of a building of a wall of a house of wall has been occupied. of a building of a structure of a plot. of land of ground. of wall of the structure of

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

    were supposed to be yearning for the time when the Church should be “purified”.⏎For two hundred years, while the world never had the least suspicion of their existence, the brotherhood transmitted by these means the wisdom of “

  2. #2 peak

    Physics Mach 1, guided with PHD Guide⏎HA 6 x 15 minutes<|endoftext|>Have you ever sat down to begin writing and not have a single idea about what to write? We are learning to generate ideas in different ways so

  3. #3 peak

    is one of the express prophecies of the Quran, which proved literally true, afterwards, whereas when this prophecy was made there seemed not to be the remotest chance that the helpless and powerless man who had come out<|endoftext|>- Study Skills.⏎

  4. #4 peak

    oring and people could find it difficult to breathe," he explained.⏎Therefore, if you have a persistent cold, it is not worth ignoring it.<|endoftext|>Never Miss a Beat: Get a snapshot of the issues affecting the IT industry straight to your inbox

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. L5:264 suppresses
  2. L2:899 weakly suppresses
  3. L1:1661 weakly suppresses
  4. L0:291 weakly excites
  5. L3:964 weakly excites
  6. L3:2653 weakly suppresses
  7. L4:12 weakly suppresses
  8. L2:1375 weakly excites
  9. L4:19 weakly suppresses
  10. L2:2242 weakly suppresses
  11. L1:2333 weakly suppresses
  12. L4:101 weakly excites
  13. L1:2680 weakly suppresses
  14. L4:1625 weakly suppresses
  15. L3:2039 weakly excites
  16. L3:2211 weakly excites
  17. L0:178 weakly suppresses
  18. L1:1674 weakly excites
  19. L5:57 weakly suppresses
  20. L3:1003 weakly excites
  21. L4:1338 weakly suppresses
  22. L5:198 weakly excites unclear: weak "and" in lists
  23. L2:681 weakly suppresses
  24. L3:1812 weakly excites

Feeds later layers

  1. L7:2272 strongly suppresses
  2. L7:1103 excites 'as' in 'not as ... as' comparisons
  3. L7:2514 excites
  4. L13:1722 excites
  5. L7:1617 suppresses
  6. L7:213 excites
  7. L13:1852 suppresses
  8. L7:2141 suppresses
  9. L8:1319 weakly excites
  10. L18:1478 weakly excites
  11. L24:3054 weakly suppresses
  12. L8:3009 weakly suppresses
  13. L17:2783 weakly excites
  14. L22:1744 weakly suppresses
  15. L21:3046 weakly suppresses 'at' in 'not at all' and 'at all'
  16. L7:1401 weakly excites
  17. L15:359 weakly excites
  18. L11:2067 weakly suppresses
  19. L15:416 weakly suppresses
  20. L13:1317 weakly suppresses
  21. L15:1683 weakly excites
  22. L16:1273 weakly excites
  23. L8:2689 weakly suppresses
  24. L22:19 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 -1.99 and -1.691 values between -1.38 and -1.082 values between -1.08 and -0.7725 values between -0.77 and -0.47679 values between -0.47 and -0.172855 values between -0.17 and 0.14319 values between 0.14 and 0.4414 values between 0.44 and 0.754 values between 0.75 and 1.055 values between 1.05 and 1.361 values between 1.36 and 1.661 values between 2.58 and 2.881 values between 9.88 and 10.19offnegativepositiveoften

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. 方式进行
  2. entimes
  3. msgs
  4. 齿
  5. 网络传播
  6. .RegisterType
  7. 培养学生
  8. 昨晚
  9. 本科生
  10. issy

Suppresses

  1. ếc
  2. /site
  3. Eğitim
  4. abilité
  5. wann
  6. blanco
  7. الفريق
  8. Marker
  9. ever
  10. okia