Neuron Explorer

Qwen3-0.6B

words right after an 'if' condition

A neuron in layer 11 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 lights up on the word just after a conditional 'if' clause in advice, such as 'if you can't find', 'if you are unsure' or 'if you have trouble'. Turning it up made the model drift toward maths questions and 'what is the value' style prompts, which has little to do with the trigger.

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens an email to the maker with the neuron already filled in).

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

    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 Peoples and Climate Change

  2. #2 peak

    a pencil or marker to sketch your newspaper layout onto your blank paper.⏎- Search through magazines and newspapers for useful shapes, images and corresponding words. If you can’t find the perfect words, create them by cutting out individual letters.⏎- Experiment with

  3. #3 peak

    ...⏎however you want Santa to look!).⏎- Close template window when done printing to return to this screen.⏎- Set page margins to zero if you have trouble fitting the template on one page (FILE, PAGE SETUP or FILE, PRINTER

  4. #4 peak

    whether you need further assessment or testing for COVID-19.⏎If you are unsure whether you need medical care, call HealthLink BC at 8-1-

  5. #5 peak

    PDF [portable document format] printable page. (If you are unable to view the printable page, download the free Adobe Acrobat Reader.)⏎Click for the

  6. #6 peak

    miss a dose of Ampicillin and are taking it regularly, take it as soon as possible. If it is almost time for your next dose, skip the missed dose and go back to your regular dosing schedule. Do not take 2

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 first" "the last" "the first" "the last" "the first" "the last" "the first" "the last" "the first" "the last" "the first" "the last"

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

    or wanting to hear. A word to describe the process of removing one’s self (and one’s own responses) is the term “mindfulness”. When we become mindful of our own biases, tendencies, and prejudices, then we are better able

  2. #2 peak

    there are a slew of possible reasons for girls’ lack of access to opportunity, one worth considering is the opportunity cost. If education brings little else but personal development, it’s easy to see why few families make it a priority.⏎But what if

  3. #3 peak

    coaching, mentoring and supporting.⏎Those teachers who are at the peak of the profession are our best resource in delivering on our most ambitious goals for young Australians. If all young people are to achieve success in a worthwhile education, teachers must demonstrate careful planning

  4. #4 peak

    share that they failed to see the logic of working to the same basic voltage in selecting their architecture, so as to be more compatible with one another. If they were compatible

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. L10:750 suppresses
  2. L7:1616 weakly suppresses
  3. L10:2062 weakly suppresses
  4. L10:534 weakly suppresses
  5. L6:2323 weakly suppresses
  6. L10:2088 weakly excites
  7. L4:2769 weakly suppresses
  8. L9:1347 weakly excites
  9. L10:2934 weakly suppresses
  10. L9:356 weakly excites
  11. L8:1866 weakly suppresses
  12. L7:1571 weakly suppresses
  13. L7:292 weakly suppresses
  14. L1:1131 weakly suppresses
  15. L8:691 weakly excites
  16. L6:1453 weakly excites
  17. L6:162 weakly excites
  18. L7:1880 weakly excites
  19. L1:1790 weakly excites
  20. L9:291 weakly suppresses
  21. L8:2468 weakly excites
  22. L10:1940 weakly suppresses
  23. L5:2588 weakly excites
  24. L3:2783 weakly suppresses

Feeds later layers

  1. L13:2785 excites
  2. L14:2642 suppresses
  3. L14:1481 suppresses
  4. L13:2364 excites
  5. L13:171 excites
  6. L12:268 excites
  7. L13:1273 excites
  8. L12:381 excites
  9. L13:1434 excites
  10. L12:2310 excites
  11. L14:2517 excites
  12. L12:193 weakly excites
  13. L12:2374 weakly excites
  14. L14:1709 weakly excites
  15. L14:1284 weakly suppresses
  16. L13:2223 weakly excites
  17. L14:2978 weakly excites
  18. L14:1126 weakly excites
  19. L18:1876 weakly suppresses
  20. L16:1342 weakly excites
  21. L13:2582 weakly suppresses
  22. L16:2228 weakly excites
  23. L16:931 weakly suppresses
  24. L14:2211 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 -1.91 and -1.791 values between -1.67 and -1.551 values between -1.31 and -1.191 values between -1.19 and -1.072 values between -0.95 and -0.832 values between -0.83 and -0.716 values between -0.71 and -0.5914 values between -0.59 and -0.4763 values between -0.47 and -0.35225 values between -0.35 and -0.23542 values between -0.23 and -0.111340 values between -0.11 and 0.011049 values between 0.01 and 0.13440 values between 0.13 and 0.25145 values between 0.25 and 0.3745 values between 0.37 and 0.4912 values between 0.49 and 0.615 values between 0.61 and 0.734 values between 0.73 and 0.854 values between 0.85 and 0.972 values between 0.97 and 1.091 values between 1.21 and 1.331 values between 1.57 and 1.691 values between 2.18 and 2.301 values between 2.78 and 2.90offnegativepositiveoften

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. genden
  2. jours
  3. 𝜂
  4. opard
  5. ocities
  6. orage
  7. contrat
  8. ляр
  9. ieux
  10. ouns

Suppresses

  1. 熙
  2. 温室
  3. psychology
  4. xbc
  5. rí
  6. attributes
  7. ICC
  8. _attributes
  9. dictionaries
  10. ares