Neuron Explorer

Qwen3-0.6B

'and' joining two clauses

A neuron in layer 17 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 lights up on the word 'and' when it joins two full sentence-like parts, such as 'she'll never be as sociable as an extrovert and that's OK'. The opposite side fires on 'and' after a comma in a list, but turning the neuron up did not give a clear theme in the writing.

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

    Remember, however, to take your teen’s natural disposition into account. If she’s an introvert she’ll never be as sociable as an extrovert and that’s OK. More importantly, with a great attitude, she’ll attract like

  2. #2 peak

    is to drive with a BAC of .08 percent.⏎Blood alcohol concentration, or BAC, describes the amount of alcohol contained in an individual’s blood and is measured as weight per unit of volume. The measurement is usually

  3. #3 peak

    teaches its readers that, in life, we must make choices, and learn to live with and move on from said choices once there is no way back to them and life has moved on. I took the one less travelled by

  4. #4 peak

    by their own living experience. Adoptees generally live a regular life similar to someone who wasn’t adopted; however, they have experiences that are unique to being adopted and these experiences may have an impact on their lives at various times throughout their lives.

  5. #5 peak

    housings, etc. Any two different metals under water will cause a small electrical current that will steadily corrode one metal. Sacrificial anodes are the solution and we’ve been using them for decades, no, make that centuries now.⏎It

  6. #6 peak

    but to maintain enough energy in general. Think about it: an ultramarathon is any race that is longer than the traditional 26.2 mile marathon and can commonly reach distances of 100 miles or more! Even short runs

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: How to, in our society, that the way, that the world, that world is, but in our eyes, we still, we have, but the world, but world, but world, but world, but world, but world

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

    experience, and seventy-six percent know of someone who has experienced seasonal depression.⏎(Male 2

  2. #2 peak

    keywords for each book and chapter.⏎If you think you should have access to this title, please contact your librarian.⏎To troubleshoot, please check our FAQs, and if you can't find the answer there, please contact us.<|endoftext|>Indigenous

  3. #3 peak

    refine, and establish clinical uses for liquid biopsy tests.⏎Different liquid biopsy<|endoftext|>Biology 1

  4. #4 peak

    copy, and fecal occult blood test.⏎- Cervical cancer: Regular Pap tests are

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. L13:131 strongly excites 'and' joining parallel phrases
  2. L16:376 suppresses 'or' joining alternatives
  3. L10:74 excites
  4. L9:92 suppresses "and" or "or" joining two items
  5. L4:57 suppresses
  6. L5:548 excites
  7. L16:1669 excites
  8. L15:1443 excites
  9. L15:727 excites
  10. L1:1250 suppresses
  11. L16:2049 excites
  12. L10:1643 suppresses
  13. L14:1639 suppresses "and" joining two nouns
  14. L4:2270 weakly excites
  15. L13:1066 weakly excites
  16. L15:44 weakly excites
  17. L12:51 weakly excites
  18. L14:1237 weakly excites
  19. L14:801 weakly excites 'and' or 'or' joining list items
  20. L14:936 weakly excites 'and' or 'or' in a list of three or more
  21. L4:108 weakly excites "or" offering a choice in web text
  22. L0:313 weakly excites "and" joining paired nouns
  23. L0:2711 weakly suppresses
  24. L6:129 weakly suppresses

Feeds later layers

  1. L19:2493 excites
  2. L19:1245 suppresses comma opening a list of parallel items
  3. L19:2416 excites
  4. L18:765 excites
  5. L19:1262 suppresses
  6. L18:1047 suppresses
  7. L18:892 suppresses
  8. L19:979 excites
  9. L18:2516 suppresses
  10. L24:224 weakly suppresses
  11. L19:3015 weakly excites
  12. L19:3001 weakly excites
  13. L26:610 weakly suppresses
  14. L22:118 weakly excites
  15. L19:1506 weakly excites
  16. L20:658 weakly excites
  17. L18:2341 weakly suppresses comma before an added clause
  18. L19:577 weakly suppresses
  19. L18:174 weakly excites
  20. L21:478 weakly suppresses
  21. L20:852 weakly suppresses
  22. L19:291 weakly excites 'and' joining two full clauses
  23. L21:739 weakly suppresses 'both X and Y' pairing words
  24. L18:2222 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 -19.00 and -18.101 values between -17.21 and -16.313 values between -16.31 and -15.411 values between -15.41 and -14.511 values between -14.51 and -13.621 values between -13.62 and -12.721 values between -11.82 and -10.932 values between -10.93 and -10.034 values between -10.03 and -9.131 values between -9.13 and -8.231 values between -7.34 and -6.441 values between -6.44 and -5.541 values between -5.54 and -4.643 values between -4.64 and -3.751 values between -3.75 and -2.855 values between -2.85 and -1.9511 values between -1.95 and -1.061762 values between -1.06 and -0.161952 values between -0.16 and 0.7447 values between 0.74 and 1.6417 values between 1.64 and 2.5312 values between 2.53 and 3.4316 values between 3.43 and 4.338 values between 4.33 and 5.2310 values between 5.23 and 6.128 values between 6.12 and 7.027 values between 7.02 and 7.927 values between 7.92 and 8.825 values between 8.82 and 9.719 values between 9.71 and 10.611 values between 10.61 and 11.512 values between 11.51 and 12.402 values between 12.40 and 13.301 values between 13.30 and 14.201 values between 14.20 and 15.102 values between 15.99 and 16.89offnegativepositiveoften

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. stand
  2. 掖
  3. 眼里
  4. "));⏎
  5. gang
  6. cek
  7. "]);⏎
  8. vested
  9. 全体员工
  10. 谈到

Suppresses

  1. orca
  2. ude
  3. icrobial
  4. .Consumer
  5. iders
  6. icerca
  7. sburg
  8. afari
  9. umeric
  10. .constructor