Neuron Explorer

Qwen3-0.6B

'one' in 'for one reason' and 'one another'

A neuron in layer 19 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

The neuron responds to the word 'one' when it means 'a particular one' or 'one another', as in 'for one reason' or 'one of the greatest'. Its strongest negative reactions are on 'Children' in names like 'St. Jude Children's Research Hospital', which is a different kind of word. Turning it down made the model repeat the fragment "'s" over and over.

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

    less comfortable expressing themselves via words. Art Therapy is also known to help people with social skills, specifically, those that are withdrawn or shy, or who, for one reason or another, have a difficult time functioning within social situations.⏎Why art?

  2. #2 peak

    whole poem, but we're just getting into it now, thirty-nine lines in. Lowell illustrates how hard, and how steadfastly, the soldiers fought for one another, and for the Republic.<|endoftext|>By the end of the session, participants

  3. #3 peak

    8, the father confirmed that Yanela and her mother stayed together with the Washington Post (Selk, 2018). They were not separated from one another like hundreds of other families who crossed the border between April and June 2

  4. #4 peak

    914). As one historian characterized this trans-Atlantic movement, it attempted “to limit the socially destructive

  5. #5 peak

    molecule with a trick like this. And that’s part of the problem: it’s so obvious that it seems like it probably wouldn’t work at all. For one thing, how do you know if your

  6. #6 peak

    reef fish abundance and distribution trends between locations. Armed with the knowledge of where<|endoftext|>Edited by William Byron Forbush This is a book that will never die — one of the great English classics. . .

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: 's' 8's' s' s' s' s' s' s' s' s' s' s' s' s' s' s' s' s' s' s' s' s' s

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

    able alternative therapies for this common disease.⏎In today’s session, Drs. Kenneth Ataga of the University of North Carolina and Russell Ware of St. Jude Children’s Research Hospital will review existing and innovative therapies for SCD.⏎Dr. At

  2. #2 peak

    prescribe medications to take during an episode of vertigo, which will lessen the severity of an attack. If Meniere’s disease is causing balance issues, vestibular rehabilitation therapy can help.⏎Low Blood

  3. #3 peak

    meeting mad characters is easy but finding your way home all the while keeping your sanity is less so.⏎Carroll, Lewis. Alice in Wonderland. Macmillan Children's Books, 2015. 208 pp., ISBN

  4. #4 peak

    , might not be immediately obvious.⏎“It is not a part of our culture to think of heat as risky,” said Bernstein, a pediatrician at Boston Children’s Hospital and co-director of the Center for Climate, Health, and the

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. L17:2369 excites
  2. L8:1541 excites
  3. L11:2179 excites
  4. L18:800 excites
  5. L18:1095 excites
  6. L18:569 excites
  7. L14:280 suppresses
  8. L18:1028 weakly excites
  9. L5:1823 weakly suppresses
  10. L18:305 weakly suppresses
  11. L8:79 weakly suppresses
  12. L6:2338 weakly excites
  13. L17:529 weakly suppresses
  14. L14:169 weakly excites
  15. L18:1103 weakly suppresses
  16. L3:59 weakly excites
  17. L16:951 weakly excites
  18. L16:1087 weakly suppresses
  19. L16:527 weakly excites
  20. L17:1535 weakly excites
  21. L15:202 weakly excites mixed, digits in URLs and comparisons
  22. L8:16 weakly suppresses
  23. L16:1683 weakly suppresses
  24. L12:336 weakly excites

Feeds later layers

  1. L22:397 strongly suppresses
  2. L26:765 strongly suppresses
  3. L22:576 strongly suppresses
  4. L25:2331 strongly suppresses
  5. L27:905 strongly suppresses
  6. L24:1505 strongly suppresses
  7. L21:1071 strongly suppresses
  8. L27:1064 strongly suppresses
  9. L20:1340 suppresses
  10. L20:1050 suppresses
  11. L22:1163 suppresses
  12. L25:1566 suppresses
  13. L27:2084 suppresses
  14. L25:127 excites
  15. L20:2278 suppresses
  16. L27:404 suppresses
  17. L20:519 suppresses
  18. L26:2244 suppresses
  19. L24:286 suppresses
  20. L20:1388 suppresses
  21. L27:355 suppresses
  22. L22:2151 excites
  23. L23:309 weakly suppresses
  24. L27:942 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 -22.50 and -21.831 values between -19.13 and -18.461 values between -11.05 and -10.371 values between -10.37 and -9.701 values between -9.02 and -8.351 values between -7.68 and -7.002 values between -7.00 and -6.332 values between -6.33 and -5.652 values between -4.31 and -3.635 values between -3.63 and -2.9610 values between -2.96 and -2.2914 values between -2.29 and -1.6119 values between -1.61 and -0.9493 values between -0.94 and -0.262343 values between -0.26 and 0.411153 values between 0.41 and 1.08244 values between 1.08 and 1.7611 values between 1.76 and 2.431 values between 2.43 and 3.111 values between 3.11 and 3.782 values between 3.78 and 4.45offnegativepositiveoften

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. 日讯
  3. _-
  4. ("{}
  5. {};
  6. ugu
  7. osa
  8. (()
  9. {};⏎
  10. /*#__

Suppresses

  1. 's
  2. ’s
  3. ´s
  4. ’S
  5. �s
  6. 的工作
  7. 'S
  8. 的手
  9. 的大
  10. 的城市