Neuron Explorer

Qwen3-0.6B

mid-phrase words in set expressions

A neuron in layer 13 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron is unclear. It fires on words in the middle of set phrases like 'one reason or another', 'such and such' and 'Which of the following motivations best explains so-and-so', and it dips on specific place and time words like 'today' in news text. Turning it up or down did not produce a clear theme.

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

    this⏎“Respected chief guest, honorable guest of honor and all the dignitaries present here, good evening and I would like to welcome you all for ………….function.”⏎After a brief introduction, there is always the inauguration of the

  2. #2 peak

    there is no single correct answer but for which there are perhaps more justifiable answers and less justifiable answers. Something like “Which of the following motivations best explains so-and-so’s actions in such-and-such novel?” Instead of posing this question

  3. #3 peak

    anks in advance. kamesh. here is the code from Marcus Mock exam 2: following code what will be the output?⏎I added UBB code here - Mapraputa [This message has been edited by Mapraputa Is (

  4. #4 peak

    , we will delve into one of Mary Oliver’s poems, analyzing its themes, literary devices, and the impact it has on readers.⏎The Poem: [Insert Poem Title]⏎[Insert the full text of the chosen Mary Oliver poem here

  5. #5 peak

    Every administrator and politician speaks of “party politics” in villages, and even villagers are often heard saying, “There is too much ‘party’ in such and such a village”. The coming of elections gives fresh opportunities for the crystallization of parties

  6. #6 peak

    ?⏎Or imagine a student who comes home from school announcing that "she had a great day because she got an A, did better than her best friend, or ... won the spelling bee." These accomplishments reflect a very different set of goals than those

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: :?? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?

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

    of the medical staff at Phoenixville Hospital. His office is located at 824 Main St., Suite 206.<|endoftext|>MEDIA RELEASE - "CLIMATE IMP

  2. #2 peak

    of the West<|endoftext|>Arsenic and Old Space: NASA to Announce New Form of Life on Earth?⏎Gizmodo is reporting that NASA's big announcement later today will be that a new form of life has been found in the harsh environment of

  3. #3 peak

    that binge drinking has reached epidemic proportions in China and argues that efforts to tackle the problem must address the country's unique drinking culture.⏎In this study, published online today in the journal Addiction, binge drinking was defined as consuming 50g or

  4. #4 peak

    passed from the hands of civilization to civilization, from generation to generation that still appears as vibrant today as the day it was struck. - (LC.025)<|endoftext|>The fur trade caused Native people to become partially dependent on European trade goods

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. L9:218 suppresses
  2. L12:2935 excites
  3. L11:1970 excites
  4. L12:2423 excites
  5. L10:1342 suppresses
  6. L9:570 excites
  7. L11:1972 suppresses
  8. L12:1788 excites
  9. L12:2684 suppresses
  10. L12:146 suppresses
  11. L11:974 suppresses
  12. L10:80 excites
  13. L12:461 suppresses
  14. L8:1506 excites
  15. L12:40 excites
  16. L10:158 excites
  17. L11:2095 suppresses
  18. L9:558 suppresses
  19. L12:26 suppresses
  20. L11:1711 weakly excites
  21. L9:27 weakly suppresses
  22. L12:955 weakly excites
  23. L9:849 weakly suppresses
  24. L9:1781 weakly suppresses

Feeds later layers

  1. L15:2255 strongly suppresses
  2. L14:1490 strongly suppresses
  3. L15:2165 suppresses
  4. L15:2525 suppresses
  5. L19:2756 suppresses
  6. L17:2138 suppresses
  7. L14:2251 suppresses
  8. L14:2067 suppresses
  9. L16:721 suppresses
  10. L14:2136 excites
  11. L15:1641 excites
  12. L14:1844 suppresses
  13. L17:2460 suppresses
  14. L17:2936 suppresses
  15. L19:2157 suppresses
  16. L14:797 excites
  17. L17:2036 excites
  18. L17:2024 suppresses
  19. L14:1604 excites
  20. L16:730 excites
  21. L15:1828 suppresses
  22. L15:1088 suppresses
  23. L15:1950 excites
  24. L14:2144 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 -2.68 and -2.521 values between -2.04 and -1.874 values between -1.71 and -1.557 values between -1.39 and -1.236 values between -1.23 and -1.0718 values between -1.07 and -0.9119 values between -0.91 and -0.7533 values between -0.75 and -0.5946 values between -0.59 and -0.43107 values between -0.43 and -0.27303 values between -0.27 and -0.111792 values between -0.11 and 0.06996 values between 0.06 and 0.22389 values between 0.22 and 0.38128 values between 0.38 and 0.5444 values between 0.54 and 0.708 values between 0.70 and 0.863 values between 0.86 and 1.021 values between 1.02 and 1.181 values between 1.34 and 1.501 values between 3.59 and 3.75offnegativepositiveoften

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. ECH
  2. iction
  3. mvc
  4. enco
  5. icted
  6. itive
  7. 贫
  8. |R
  9. ics
  10. pel

Suppresses

  1. yourselves
  2. "><?=$
  3. љ
  4. ...">⏎
  5. ście
  6. Whatever
  7. 讓他們
  8. ...\
  9. )...
  10. ...');⏎