Neuron Explorer

Qwen3-0.6B

"but" in "not only X, but" phrases

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

This neuron lights up on the word "but" when a sentence has the pattern "not only this, but also that". It is a very consistent trigger, but turning it up or down only produced loose or broken text, so the steering does not show a clear effect.

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

    . Active student participation is not only encouraged, but required.⏎At some institutions, Logic & Proofs has been offered as a fully

  2. #2 peak

    you providing lots of information and historical details within the given amount of words and pages. It is essential to include not only related to a certain historical event information, but also to show a coherent, profound manner of analyzing. You are expected to demonstrate

  3. #3 peak

    women in newspaper work not only to write the news, but to make it.”⏎Marjory Lang, Women Who Made the News (2

  4. #4 peak

    you must understand and apply some crucial National Electrical Code rules and regulation. Following these rules to the letter will not only assure you that your work will pass inspection, but that it will be a safe installation as well. Improperly installed recessed

  5. #5 peak

    your phone and go back to your routine. But this might change soon. Now, your shoes can not only count your steps but also study them.⏎“This means that now you can understand how your feet are being

  6. #6 peak

    also being seen adopting Pilates exercises. The coaches and athletes are not only using pilates to benefit from improving core strength and flexibility, but also to prevent injuries. Pilates aids the athletes capacity in their field. If

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: this this for 8 years 36. 3 6 3 .... 5 ... ... 5 6

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

    . In so doing, you might be aiding your youngster to be a far better thinker and<|endoftext|>Take any point P inside an equilateral triangle. Draw PA, PB and PC⏎from P perpendicular to the sides of the triangle where A, B

  2. #2 peak

    letter words⏎6 letter words⏎5 letter words⏎4 letter words⏎3 letter words⏎2 letter words⏎Images for ZEATINSLoading...⏎SCRABBLE is the registered trademark of Hasbro and J.W. Spear & Sons Limited

  3. #3 peak

    neck etc. of daevic beings (see DĒW), and mentioned manaoθrī- as the corresponding ahuric word (AirWb., cols. 530, 1126; cf.

  4. #4 peak

    activation of the kinases leads to the initiation of downstream restoration pathways. Likewise, in response to Ataluren pontent inhibitor solitary strand breaks in DNA (SSBs), PARP1 as well as the MRN complicated initiate repair from

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. L1:4 strongly excites
  2. L0:825 strongly suppresses
  3. L2:1855 strongly excites
  4. L4:1319 strongly excites the 'B' in vitamin B
  5. L16:260 excites
  6. L16:374 excites
  7. L10:201 suppresses the letter B in vitamin names
  8. L7:520 suppresses
  9. L6:1357 excites
  10. L16:75 suppresses
  11. L7:2095 excites
  12. L10:887 suppresses the B in vitamin B names
  13. L16:134 excites
  14. L6:328 suppresses
  15. L16:160 excites
  16. L16:827 suppresses
  17. L0:1638 suppresses
  18. L16:215 suppresses
  19. L16:671 excites
  20. L5:138 excites
  21. L16:249 excites
  22. L15:129 suppresses
  23. L16:1079 suppresses "by" after a past participle
  24. L16:1358 excites

Feeds later layers

  1. L20:256 strongly excites
  2. L20:174 suppresses
  3. L19:370 suppresses
  4. L18:328 suppresses
  5. L18:242 excites
  6. L18:198 suppresses
  7. L18:474 suppresses
  8. L18:404 suppresses 'get', 'go' and 'got' after a subject
  9. L18:344 suppresses
  10. L19:583 excites
  11. L18:1493 suppresses
  12. L18:205 suppresses
  13. L18:102 suppresses
  14. L18:385 excites
  15. L18:936 suppresses
  16. L18:365 suppresses
  17. L20:211 suppresses
  18. L19:197 suppresses
  19. L22:2245 excites
  20. L20:183 suppresses
  21. L18:103 suppresses
  22. L19:569 suppresses
  23. L21:706 excites
  24. L19:754 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.

187 values between -1.04 and -0.681574 values between -0.68 and -0.311718 values between -0.31 and 0.06216 values between 0.06 and 0.4357 values between 0.43 and 0.8031 values between 0.80 and 1.1714 values between 1.17 and 1.5311 values between 1.53 and 1.906 values between 1.90 and 2.2711 values between 2.27 and 2.644 values between 2.64 and 3.014 values between 3.01 and 3.379 values between 3.37 and 3.747 values between 3.74 and 4.117 values between 4.11 and 4.4811 values between 4.48 and 4.855 values between 4.85 and 5.213 values between 5.21 and 5.583 values between 5.58 and 5.953 values between 5.95 and 6.326 values between 6.32 and 6.693 values between 6.69 and 7.052 values between 7.05 and 7.421 values between 7.42 and 7.792 values between 7.79 and 8.163 values between 8.16 and 8.532 values between 8.53 and 8.904 values between 8.90 and 9.261 values between 11.10 and 11.471 values between 12.58 and 12.941 values between 12.94 and 13.311 values between 13.31 and 13.68offnegativepositiveoften

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. heading
  2. gest
  3. venue
  4. trand
  5. urst
  6. hev
  7. кров
  8. 卖给
  9. tester
  10. 可惜

Suppresses

  1. yum
  2. igue
  3. wort
  4. inic
  5. irty
  6. eus
  7. uits
  8. WG
  9. еть
  10. minut