Neuron Explorer

Qwen3-0.6B

'and so on' list endings

A neuron in layer 22 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 that leads into 'and so on' at the end of a list, such as 'and so' or 'and on'. Turned down, the model wrote long strings of dots, which is the opposite of how it normally ends a list.

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

    instance, if you are thinking of the number 1, it would be "A". Number 2 would be "B". 3 is "C", and so on.⏎- Now, think of a country that starts with the letter you

  2. #2 peak

    together. This skill is important in other areas of their lives as they continue to grow, such as writing, tying shoes, typing and so much more⏎2)Fine Motor Coordination– In order to draw shapes,

  3. #3 peak

    is so humble you could argue it doesn’t really have its own name. After all, do its various monikers: lavatory, bog, khazi and so on, denote the room or the device? Or both? It can be hard

  4. #4 peak

    question of priority (individual or community) often has the largest impact in the most pressing ethical questions: health care, abortion, multiculturalism, hate speech, and so on. . . .⏎Beginning in the late 20th century, many

  5. #5 peak

    ox, hepatitis, chicken pox, pneumonia, and measles, and so had never developed any immunityImmunity⏎Resistance to disease, developed naturally or through

  6. #6 peak

    among many others.⏎An academic journal also publishes different research types. Some of these include original articles, reviews, book reviews, case studies, short communications, and so on. Usually, bigger journals publish a wider variety of research works.⏎One vital

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: ................................................................................................................................................

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

    tested how individuals group rhythms by playing simple sequences of tones. For example, listeners are presented with tones that alternate in loudness (...loud-soft-loud-soft...) or duration (...long-short-long-short...) and are asked to indicate their perceived

  2. #2 peak

    center activities!⏎- Engaging morning work!⏎- Homework variety!⏎- Individual pages for facts 1-12 (-1, -2, -3, etc. up to -12)⏎- Mixed facts practice pages⏎- Answer

  3. #3 peak

    For instance, if you are thinking of the number 1, it would be "A". Number 2 would be "B". 3 is "C", and so on.⏎- Now, think of a country that starts with the letter

  4. #4 peak

    from a study of statistics.⏎Why can a yield never be modelled exactly by a normal⏎How are the sums of 2, 3, 4, ... identical normal⏎Why is the mean target of 8000 tonnes

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. L18:2722 strongly suppresses
  2. L17:2866 strongly suppresses
  3. L19:1265 strongly suppresses
  4. L21:2493 strongly excites
  5. L18:2185 suppresses
  6. L18:2938 excites
  7. L18:1118 excites
  8. L17:2209 excites
  9. L17:2664 excites
  10. L16:1603 suppresses
  11. L17:902 excites
  12. L20:1620 excites
  13. L16:2542 suppresses
  14. L18:2305 excites
  15. L21:2512 excites
  16. L16:685 excites
  17. L14:564 suppresses
  18. L19:2164 suppresses
  19. L13:2740 excites
  20. L15:2255 excites
  21. L17:2578 excites
  22. L11:1527 excites
  23. L19:1246 excites
  24. L15:2610 excites

Feeds later layers

  1. L27:426 strongly suppresses
  2. L25:454 strongly suppresses
  3. L25:717 strongly suppresses
  4. L25:1326 strongly suppresses ellipsis dots after a cut-off quote
  5. L26:295 strongly suppresses
  6. L26:472 suppresses
  7. L27:502 suppresses
  8. L27:764 suppresses
  9. L23:641 suppresses
  10. L27:1536 weakly suppresses
  11. L26:943 weakly suppresses
  12. L23:2015 weakly excites
  13. L27:1182 weakly suppresses
  14. L27:606 weakly excites
  15. L24:2694 weakly excites
  16. L26:422 weakly excites
  17. L26:417 weakly suppresses
  18. L27:475 weakly suppresses
  19. L27:1899 weakly suppresses
  20. L23:819 weakly suppresses
  21. L25:1135 weakly suppresses
  22. L26:369 weakly suppresses
  23. L23:40 weakly suppresses
  24. L23:260 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 -52.38 and -50.971 values between -29.88 and -28.481 values between -18.63 and -17.232 values between -15.82 and -14.421 values between -14.42 and -13.013 values between -11.60 and -10.204 values between -10.20 and -8.795 values between -7.39 and -5.9817 values between -5.98 and -4.5733 values between -4.57 and -3.1757 values between -3.17 and -1.76239 values between -1.76 and -0.363359 values between -0.36 and 1.05183 values between 1.05 and 2.462 values between 2.46 and 3.86offnegativepositiveoften

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. #",
  2. 呙
  3. %%*/
  4. ipel
  5. ')['
  6. ancybox
  7. 何况
  8. )'],⏎
  9. )','
  10. ']."'

Suppresses

  1. ...
  2. ...
  3. …
  4. ……
  5. ...,
  6. ....
  7. ......
  8. ...</
  9. ..."
  10. ...⏎