Neuron Explorer

Qwen3-0.6B

"nothing/something to" before 'do' or 'be'

A neuron in layer 4 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

Fires on the word "to" right after "nothing" or "anything" or "something", as in "nothing to do with" or "anything to be seen." Turning it up made the model write long, rambling text that did not clearly change theme.

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

    the earth. They don’t have anything to do with Pilgrims, of course, but were a tradition recounted in many

  2. #2 peak

    atypical from the others because of that. In a way if you don’t share your memories, people will find you boring and dull, because you have nothing to talk about, because everything you talk about is a memory. A person cannot talk

  3. #3 peak

    of this humongous ship, but many believe it had something to do with low grade rivets.⏎Wealthier passengers were offered luxurious dining tables

  4. #4 peak

    ictions like gambling, that have nothing to do with food. Tolerance is both a result and a cause of addictive behavior

  5. #5 peak

    their inventions: a 3D-printed laundry soap box that keeps an eye on its volume and orders more when it’s running down.⏎Without any power source to worry about, these devices are decidedly eco-friendly, and very cheap to manufacture.⏎

  6. #6 peak

    Before DNA sequencing, when bacteria were classified morphologically, W. persica and W. melaphagi were also thought to be related, but these have nothing to do with the famous Wolbachia (W. persica is a

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 other one, and I have to be there too. I need to be there too. Are you sure you want to get through the door in this 300 photoshoot of the human being, the other one, and I

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

    not the norm,” said Joe Walsh, a member of the Friends of Matthias Baldwin Park, in an email to National Review. “He was BLM [Black Lives Matter] before there was a slogan.”⏎‘The irony of vandalizing a monument

  2. #2 peak

    Coalition for Western Women’s History decries this ongoing violence against Black women and men and stands in solidarity and support with Black Lives Matter. As scholars of the history of women, gender, and sexuality we want

  3. #3 peak

    54th Union Army regiment, the first all-volunteer black regiment. The sculpture, dedicated to black soldiers, is located in Boston.⏎The Black Lives Matter protests and violent riots were sparked by the death of George Floyd, a black

  4. #4 peak

    of neglect they have experienced in America both in life and in death.⏎We also want to acknowledge and amplify the work that Black women activists have done in founding Black Lives Matter (Patrisse Khann-Cullors, Alicia Garza, and

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. L2:111 weakly suppresses
  2. L2:126 weakly excites
  3. L3:456 weakly suppresses
  4. L3:950 weakly excites
  5. L0:943 weakly suppresses
  6. L2:1608 weakly suppresses
  7. L3:1712 weakly excites
  8. L2:1935 weakly suppresses
  9. L3:1698 weakly excites
  10. L3:1055 weakly excites
  11. L0:1103 weakly excites
  12. L3:2398 weakly excites
  13. L2:2462 weakly excites
  14. L2:2248 weakly suppresses
  15. L3:1015 weakly excites
  16. L0:786 weakly suppresses
  17. L2:2782 weakly suppresses
  18. L0:125 weakly suppresses
  19. L0:3066 weakly excites
  20. L3:2368 weakly suppresses
  21. L3:1306 weakly suppresses
  22. L1:2008 weakly excites
  23. L3:2879 weakly excites
  24. L1:1209 weakly excites

Feeds later layers

  1. L15:203 weakly excites
  2. L5:2538 weakly excites
  3. L5:1969 weakly excites
  4. L5:2289 weakly suppresses
  5. L10:2155 weakly excites
  6. L6:2211 weakly excites
  7. L6:2846 weakly suppresses
  8. L9:285 weakly excites
  9. L20:1702 weakly suppresses
  10. L15:2014 weakly excites
  11. L13:2296 weakly suppresses
  12. L17:608 weakly excites
  13. L22:2405 weakly suppresses
  14. L25:1699 weakly suppresses
  15. L8:2640 weakly excites
  16. L14:938 weakly suppresses
  17. L20:1956 weakly excites
  18. L8:2449 weakly suppresses
  19. L10:3000 weakly suppresses
  20. L5:1206 weakly suppresses
  21. L11:666 weakly suppresses
  22. L5:2742 weakly excites
  23. L15:1633 weakly suppresses
  24. L13:844 weakly suppresses 'of' after a percentage or share

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.

2 values between -0.76 and -0.692 values between -0.69 and -0.621 values between -0.62 and -0.551 values between -0.55 and -0.483 values between -0.48 and -0.4115 values between -0.41 and -0.3446 values between -0.34 and -0.27153 values between -0.27 and -0.20343 values between -0.20 and -0.13631 values between -0.13 and -0.061005 values between -0.06 and 0.01810 values between 0.01 and 0.08495 values between 0.08 and 0.15240 values between 0.15 and 0.22102 values between 0.22 and 0.2931 values between 0.29 and 0.3610 values between 0.36 and 0.439 values between 0.43 and 0.503 values between 0.50 and 0.572 values between 0.57 and 0.641 values between 0.71 and 0.781 values between 0.78 and 0.851 values between 1.27 and 1.331 values between 1.96 and 2.03offnegativepositiveoften

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. enses
  2. agoon
  3. 法
  4. isArray
  5. AdminController
  6. 目的
  7. adoras
  8. 伊斯
  9. reason
  10. NAS

Suppresses

  1. gnu
  2. 坟
  3. bersome
  4. 绩
  5. 邮
  6. ombre
  7. 等奖
  8. tire
  9. tree
  10. ẩn