Neuron Explorer

Qwen3-0.6B

"with" after a noun, introducing contents

A neuron in layer 9 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 "with" when it follows a noun and describes what that noun includes or comes with, like "a complete history with facts" or "a timeline with points". It is quieter, and sometimes negative, on "with" after a verb that names a partner, like "curry favour with". Turning it up did not give a clear theme in the output.

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

    in different cultures, and how it could be used to improve human relations. Learn more:<|endoftext|>.45-70 Government Ballistics⏎A complete history with facts, uses, pros, cons, and ballistic information.⏎45-7

  2. #2 peak

    legislated by the Mexican Federal Government and ruled by the Federal Labor Laws under Article 74. Employees, public and private, are entitled to the day off with or without pay, a fact that I have had conflicting information for. Supposed

  3. #3 peak

    this activity, but this is a good opportunity to remind them that even an ordinary incident can be retold in an exciting way.⏎The activity involves making a timeline with points they choose from their lives, and then freew

  4. #4 peak

    Email Based, Online Homework Assignment Help in Classification Of Relays⏎Transtutors is the best place to get answers to all your doubts regarding classification of relays with examples. Transtutors has a vast panel of experienced in classification of relays

  5. #5 peak

    link to download ebooks to your computer. Orders paid by PayPal require up to 8 business hours to verify payment and release electronic media. For immediate downloads, payment with credit card is required.⏎This math unit presents four activity pages in which students read

  6. #6 peak

    SHOKÉ,⏎LESSONS IN ELEMENTARY PHY-⏎PHYSIOLOGY. By Sir MICHAEL FOSTER,⏎K.C.B., M.D. With Illustrations. Pott 8vo. 15.⏎Sir MICHA

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: What is the value of the expression $2020^2 - 2020$? Let me think... I don't know what 2020 is, but it's not 2020,

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

    them throughout the period when other, similar regimes curtailed Jewish rights to curry favor with the Nazis. Still, Salazar didn’t want more Jews settling permanently in his

  2. #2 peak

    A Comparison Of High-Level And Low-Level Programming Languages⏎A way to categorize programming languages is through high-level or low-level. The low-level languages communicate directly with the central processing unit or the CPU. They can perform very basic commands but are

  3. #3 peak

    Require school police and related security officers to have training in adolescent development.⏎- Attempt to reconnect alienated youth or students who are at-risk for behavior problems or violence with the mainstream student body. Use threat-assessment procedures to identify those at risk before

  4. #4 peak

    inscribe their names in the book of life for yet another year. Religious Jewish people work diligently to perform mitzvot (good deeds) to find favor with God during the 10 days of repentance between Rosh Hashanah

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. L4:882 strongly suppresses 'with' after provide or familiarize
  2. L2:863 suppresses
  3. L0:2342 suppresses
  4. L5:910 excites
  5. L5:763 suppresses
  6. L6:2407 suppresses
  7. L5:28 weakly excites
  8. L1:1452 weakly excites
  9. L8:2991 weakly suppresses
  10. L4:1462 weakly suppresses
  11. L6:1627 weakly suppresses
  12. L2:274 weakly excites
  13. L0:1716 weakly suppresses
  14. L6:2613 weakly excites
  15. L7:176 weakly excites
  16. L5:1694 weakly excites
  17. L1:2082 weakly excites
  18. L8:1575 weakly excites
  19. L6:1184 weakly suppresses
  20. L3:2840 weakly suppresses
  21. L5:748 weakly suppresses
  22. L7:476 weakly suppresses
  23. L7:1443 weakly suppresses
  24. L3:2999 weakly suppresses

Feeds later layers

  1. L16:1860 excites
  2. L21:1060 excites
  3. L17:2363 excites
  4. L14:1049 excites
  5. L16:2035 excites 'of' after a noun phrase
  6. L12:2058 excites
  7. L25:1883 excites
  8. L17:2463 weakly excites
  9. L17:2436 weakly excites
  10. L18:2711 weakly excites
  11. L10:1839 weakly excites
  12. L17:2009 weakly excites
  13. L20:2525 weakly excites
  14. L14:2290 weakly excites
  15. L10:886 weakly excites
  16. L17:2527 weakly suppresses
  17. L23:1875 weakly excites
  18. L18:1068 weakly excites
  19. L14:1478 weakly excites
  20. L19:2406 weakly excites
  21. L16:2988 weakly excites
  22. L17:1728 weakly suppresses
  23. L15:504 weakly excites
  24. L18:2123 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 -1.79 and -1.632 values between -1.63 and -1.471 values between -1.15 and -0.981 values between -0.82 and -0.6610 values between -0.66 and -0.5061 values between -0.50 and -0.34412 values between -0.34 and -0.181389 values between -0.18 and -0.021610 values between -0.02 and 0.15355 values between 0.15 and 0.3136 values between 0.31 and 0.4714 values between 0.47 and 0.634 values between 0.63 and 0.791 values between 0.79 and 0.955 values between 1.11 and 1.281 values between 1.28 and 1.441 values between 1.44 and 1.601 values between 1.60 and 1.761 values between 1.92 and 2.081 values between 3.37 and 3.531 values between 4.50 and 4.66offnegativepositiveoften

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. bearing
  2. ])**
  3. 高达
  4. uncomp
  5. pied
  6. partials
  7. ឥ
  8. outh
  9. fines
  10. 浓厚

Suppresses

  1. rice
  2. 哪里
  3. ично
  4. rire
  5. 干嘛
  6. thane
  7. cly
  8. 干什么
  9. 哪个
  10. 化进程