Neuron Explorer

Qwen3-0.6B

"to" after adjectives like obvious or meaning

A neuron in layer 6 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 responds to the word "to" when it follows words like "obvious", "meaning" or "different", as in "obvious to me" or "what freedom means to me". Turning it up made the text wander into unrelated topics.

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

    Susan L. Holdt, Bertrand Jacquemin and Céline Rebours<|endoftext|>Performing well in college means everything to college students.⏎So much so, that as many as 87% of

  2. #2 peak

    was no color bar at Cooper Union. Cooper demanded only a willingness to learn and a commitment to excellence, and in this he manifestly succeeded.⏎It was obvious to Cooper that not everyone would be able to enroll

  3. #3 peak

    unfortunate. Software patents impede innovation, and don’t benefit the public. If you find prior art that shows any of this method is not new or is obvious to a person trained in the art, then let the world know.<|endoftext|>Should you

  4. #4 peak

    this essay would be for her. She simply wrote the following from her heart:⏎Freedom is a word that has different meanings to everyone. So what does freedom mean to me? Well, it is the describing word for our country. It’s the

  5. #5 peak

    the movie my notions were challenged when I noticed that this video was going to be silent. It only happened to me for a couple seconds and then it became obvious to me that there was no other way to make a video about this matter than sound

  6. #6 peak

    es⏎- Back hole, arse, butt, bussy⏎- Breasts, chest, breast tissue, boobs, tits⏎Sex can mean different things to different people. Sex can include vaginal, anal, oral, hand jobs or fing

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: "I have a question about the number of times the number of times the number of times the number of times the number of times the number of times the number of times the number of times the number of times the number of times the number

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

    DataTableCollection. Dim tablesCollection As DataTableCollection = thisDataSet.Tables ' Get a specific table by name. Dim table As DataTable = tablesCollection("Suppliers") Console.WriteLine(table.TableName) End Sub⏎Available since 1.1<|endoftext|>A musical

  2. #2 peak

    sectable) and who have symptoms like weight loss, nausea, buildup of fluid in the abdomen (ascites) and a poor⏎Margins in surgery @(Model.HeadingTag)>⏎Margin is the area of healthy tissue surrounding a tumour that is

  3. #3 peak

    teachers must demonstrate careful planning, challenging goals, creative use of resources, varied and effective teaching strategies and awareness of their own strengths and weaknesses.⏎The standards set the bar high because the<|endoftext|>At the higher data link layer of communication, asynchrony

  4. #4 peak

    ise symptoms in a Lancet paper. At a much less sophisticated level, PutnamPig’s “Swine Flu Song” on Youtube http://www.youtube.com/watch?v=tbt_PuVAVTU defends pigs against unfair stigmatisation

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. L4:1765 excites
  2. L4:1183 weakly suppresses
  3. L3:1229 weakly excites
  4. L4:949 weakly excites
  5. L3:213 weakly suppresses
  6. L4:1896 weakly suppresses
  7. L1:1766 weakly suppresses
  8. L4:792 weakly excites
  9. L0:2594 weakly suppresses
  10. L1:1674 weakly excites
  11. L1:257 weakly suppresses
  12. L0:1672 weakly suppresses
  13. L5:1524 weakly suppresses
  14. L5:1376 weakly suppresses
  15. L4:939 weakly excites
  16. L2:3033 weakly excites
  17. L5:2251 weakly suppresses
  18. L4:271 weakly excites
  19. L3:1865 weakly suppresses
  20. L3:1920 weakly excites
  21. L1:1367 weakly suppresses
  22. L0:2432 weakly suppresses
  23. L5:1409 weakly suppresses
  24. L2:3039 weakly suppresses

Feeds later layers

  1. L15:451 suppresses
  2. L11:1047 suppresses pieces of software and library names
  3. L7:304 excites
  4. L8:509 suppresses
  5. L18:274 suppresses
  6. L10:457 excites
  7. L21:2438 excites
  8. L9:226 suppresses 'to' starting an infinitive
  9. L9:1627 excites
  10. L26:970 weakly excites
  11. L19:913 weakly suppresses
  12. L19:745 weakly suppresses
  13. L14:1248 weakly suppresses
  14. L13:1401 weakly suppresses
  15. L25:343 weakly excites
  16. L19:1596 weakly suppresses
  17. L7:2766 weakly excites
  18. L21:1476 weakly excites
  19. L10:678 weakly suppresses
  20. L17:742 weakly suppresses
  21. L17:1674 weakly suppresses
  22. L9:654 weakly excites
  23. L16:2366 weakly suppresses
  24. L7:26 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.

4 values between -0.91 and -0.841 values between -0.69 and -0.622 values between -0.55 and -0.487 values between -0.48 and -0.4132 values between -0.41 and -0.3492 values between -0.34 and -0.27206 values between -0.27 and -0.20426 values between -0.20 and -0.12667 values between -0.12 and -0.051036 values between -0.05 and 0.02743 values between 0.02 and 0.09355 values between 0.09 and 0.16184 values between 0.16 and 0.2374 values between 0.23 and 0.3035 values between 0.30 and 0.3817 values between 0.38 and 0.456 values between 0.45 and 0.524 values between 0.52 and 0.592 values between 0.59 and 0.663 values between 0.66 and 0.731 values between 0.73 and 0.801 values between 0.80 and 0.871 values between 0.95 and 1.021 values between 1.09 and 1.162 values between 1.23 and 1.301 values between 1.30 and 1.371 values between 1.44 and 1.521 values between 1.52 and 1.591 values between 1.80 and 1.872 values between 1.87 and 1.94offnegativepositiveoften

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. essor
  2. essional
  3. orman
  4. tant
  5. 各行
  6. ]>⏎
  7. 你自己
  8. 毕竟是
  9. 蒟
  10. 大型

Suppresses

  1. 善
  2. .d
  3. .de
  4. ::
  5. -icons
  6. .uni
  7. /icons
  8. 마
  9. 원
  10. .get