Neuron Explorer

Qwen3-0.6B

'other' after 'among' in lists

A neuron in layer 11 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 lights up on the word 'other' in phrases like 'among other things', and on similar words such as 'many' in 'among many other applications'. When it was turned up, the model's writing drifted into repeated, unrelated phrases.

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

    , cannabis is produced from cannabis leaves, and marijuana, in turn, is a plant that is grown, among other things, for consumption and to make users ‘high’. Thus, we can safely

  2. #2 peak

    Hugo Chávez was elected for a third six-year term.Top of page⏎Venezuela had one of the highest murder rates in Latin America due, among other factors, to the uncontrolled availability of firearms and ammunition. There also were concerns

  3. #3 peak

    their study had found correlation rather than causation between nuclear and renewables, and emissions, they based their conclusions on the assumption of causality, he said, among other things.⏎Interpreting the correlation between events or trends as causality is a

  4. #4 peak

    pressure sensors. These electronics can one day be wrapped around prosthetic hands to provide a sense of touch or to create wearable electronics for long term body sensing, among many other possible applications. The team’s devices are so sensitive that they can detect the

  5. #5 peak

    dropower and invented, among many other things, a bladeless steam turbine, the first remote-controlled torpedoes and

  6. #6 peak

    were allowed to work and shop there but could not live there. Application of the Group Areas Act became very lax in the 1980s, among other things because courts were not able to handle all the cases, and when the Act

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 number of the last two digits, the number of the year, and the month/day, and the day of the week... the number of the last two digits, in some cases, in some cases, the day of the week,

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

    to cooler areas. Keeping this in mind, the refrigeration cycle consists of seven stages:⏎1. Compression of the hot gas;⏎6. Evaporation; and⏎A basic vapor-compression refrigeration system consists of four primary components: a meter

  2. #2 peak

    Keywords: viral marketing, word-of-mouth marketing, consumption patterns, information traits, credibility.⏎ANTHEUNIS, M.L., & REIJMERSDAL, E.A. (2012). Social

  3. #3 peak

    addus VC, Light RW. Pleural effusion. In: Mason RJ, Murray JF, Broaddus VC, et al., eds. Murray and Nadel's Textbook of Respiratory Medicine. 5th ed.

  4. #4 peak

    page⏎Patterns of tree-liana interactions: distribution and host preference of lianas in a tropical dry evergreen forest in India.⏎Vivek, P., & Parthasarathy, N.⏎Lianas are structurally dependent life-form

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 strongly excites
  2. L9:92 suppresses "and" or "or" joining two items
  3. L8:1605 suppresses
  4. L10:667 excites commas inside lists of names
  5. L8:1783 excites
  6. L5:548 excites
  7. L10:2717 excites
  8. L5:776 excites
  9. L6:620 excites "and" in lists of three or more
  10. L8:986 excites
  11. L8:664 excites
  12. L8:1789 excites
  13. L5:531 excites
  14. L4:57 suppresses
  15. L6:363 excites
  16. L10:3020 weakly suppresses
  17. L8:1046 weakly suppresses
  18. L8:1047 weakly excites
  19. L8:1238 weakly excites
  20. L9:1656 weakly excites
  21. L6:41 weakly excites
  22. L5:965 weakly excites
  23. L1:2591 weakly suppresses
  24. L5:880 weakly excites

Feeds later layers

  1. L12:1440 strongly suppresses
  2. L16:2442 strongly suppresses
  3. L14:1116 suppresses 'and' inside lists
  4. L17:919 excites
  5. L14:2054 excites
  6. L14:1635 excites end of document token
  7. L13:1941 suppresses
  8. L15:132 suppresses
  9. L15:3020 suppresses
  10. L15:2277 suppresses
  11. L18:486 suppresses
  12. L15:60 suppresses
  13. L13:497 suppresses
  14. L13:1734 suppresses sentence end right before a line break
  15. L12:1603 excites
  16. L13:1389 excites
  17. L14:449 weakly excites
  18. L16:1447 weakly excites
  19. L12:925 weakly suppresses
  20. L15:273 weakly suppresses
  21. L12:1884 weakly excites
  22. L13:1063 weakly excites
  23. L14:2531 weakly suppresses
  24. L14:683 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 -3.93 and -3.781 values between -3.46 and -3.302 values between -2.98 and -2.823 values between -2.82 and -2.671 values between -2.67 and -2.511 values between -2.51 and -2.353 values between -2.19 and -2.033 values between -2.03 and -1.873 values between -1.87 and -1.723 values between -1.72 and -1.567 values between -1.56 and -1.405 values between -1.40 and -1.248 values between -1.24 and -1.0815 values between -1.08 and -0.9217 values between -0.92 and -0.7722 values between -0.77 and -0.6137 values between -0.61 and -0.4570 values between -0.45 and -0.29188 values between -0.29 and -0.131889 values between -0.13 and 0.031111 values between 0.03 and 0.19301 values between 0.19 and 0.34113 values between 0.34 and 0.5046 values between 0.50 and 0.6624 values between 0.66 and 0.8214 values between 0.82 and 0.989 values between 0.98 and 1.145 values between 1.14 and 1.302 values between 1.45 and 1.611 values between 1.77 and 1.931 values between 1.93 and 2.091 values between 2.09 and 2.251 values between 2.25 and 2.40offnegativepositiveoften

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. נת
  2. MPG
  3. 好不好
  4. PACE
  5. LIK
  6. PATCH
  7. 皇后
  8. descricao
  9. 吠
  10. besch

Suppresses

  1. iments
  2. uml
  3. elist
  4. ctions
  5. ibel
  6. 两项
  7. iem
  8. erring
  9. ành
  10. oot