Neuron Explorer

Qwen3-0.6B

end of document and web boilerplate

A neuron in layer 10 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 fires most strongly at the seam where one web page ends and another begins, or in page furniture like 'Skip to main content' and 'Deposited By:'. It is mostly a marker for the edges of scraped page text. Turning it up gave text with no clear link to this pattern.

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

    will give a useful input to those interested in Artificial Intelligence in education.⏎|Subjects:||L Education > L Education (General)|⏎|Deposited By:||Zaidatun Tasir|⏎|Deposited On:||2

  2. #2 peak

    VS is a promising alternative strategy to produce the functional and thermostable reverse transcriptase.⏎All Science Journal Classification (ASJC) codes⏎- Insect Science<|endoftext|>An account of the religion of

  3. #3 peak

    .⏎ASJC Scopus subject areas⏎- Electronic, Optical and Magnetic Materials⏎- Ceramics and Composites⏎- Condensed Matter Physics⏎- Materials Chemistry<|endoftext|>Humans are intimately connected with the physical environment, even though we have only been present

  4. #4 peak

    Choose the book you like when you register 4.⏎Discussion questions for ‘The Death and Life of the Great Lakes’⏎Skip to search form Skip to main content You are currently offline. Some features of the site may not work correctly. They

  5. #5 peak

    -835-5322 (TTY) or at email@example.com.<|endoftext|>Table of Contents :⏎Top Suggestions Senior Kindergarten Writting Worksheet :⏎Senior Kindergarten Writting Worksheet In this worksheet your students will practice their handwriting

  6. #6 peak

    about it<|endoftext|>Press Release 07-030⏎Survey Reveals Family Ties

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:So this is a problem about:This is athis isomething...this isomething...this isomething...this isomething...thisomething...thisisomething...thisisomething...thisisomething...thisisomething...thisisomething

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

    two different numbers cant have the same cube). Therefore, by Definition 1, is one-to-one....⏎View Full Document⏎- Spring '09<|endoftext|>part of speech: noun⏎definition 1: an

  2. #2 peak

    –2. Sign up to view the full content.⏎This preview has intentionally blurred sections. Sign up to view the full version.View Full Document⏎Unformatted text preview: 60 | | | | CHAPTER 1 FUNCTIONS AND MODELS Not

  3. #3 peak

    This preview has intentionally blurred sections. Sign up to view the full version.View Full Document⏎Unformatted text preview: itself, and if ( ) ( ) lim lim x c x c h

  4. #4 peak

    prior to enrolling in the course. She obtained the following five number summary:⏎Use this information to draw a boxplot of the reading speed.⏎Answer to relevant QuestionsThe following

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. L9:223 suppresses
  2. L7:45 suppresses
  3. L8:368 suppresses
  4. L9:1934 excites
  5. L9:1301 excites
  6. L9:1201 excites
  7. L8:490 excites
  8. L9:1750 excites
  9. L4:761 suppresses
  10. L6:2905 suppresses
  11. L2:1049 excites
  12. L7:456 excites
  13. L8:1984 suppresses
  14. L9:2861 suppresses
  15. L3:255 weakly excites
  16. L6:49 weakly suppresses
  17. L6:1873 weakly suppresses
  18. L8:639 weakly suppresses
  19. L9:1265 weakly excites
  20. L4:821 weakly excites
  21. L5:11 weakly excites
  22. L1:1943 weakly excites
  23. L4:703 weakly suppresses
  24. L5:780 weakly suppresses

Feeds later layers

  1. L14:487 suppresses
  2. L11:17 suppresses
  3. L17:1360 suppresses
  4. L13:983 suppresses
  5. L11:171 excites
  6. L14:2348 suppresses
  7. L12:1109 suppresses end of document token
  8. L11:1619 suppresses
  9. L15:145 excites
  10. L11:62 excites
  11. L13:283 suppresses
  12. L12:1386 suppresses
  13. L12:2905 suppresses
  14. L11:29 excites
  15. L12:1145 suppresses
  16. L14:1315 suppresses
  17. L21:2689 suppresses
  18. L11:1826 suppresses
  19. L16:20 excites
  20. L12:2758 suppresses
  21. L18:1341 suppresses
  22. L13:1443 suppresses
  23. L15:1620 suppresses period ending a sentence in essays
  24. L11:122 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.

1 values between -3.38 and -3.201 values between -2.17 and -1.991 values between -1.99 and -1.822 values between -1.82 and -1.652 values between -1.65 and -1.484 values between -1.48 and -1.303 values between -1.30 and -1.137 values between -1.13 and -0.963 values between -0.96 and -0.782 values between -0.78 and -0.611 values between -0.61 and -0.4411 values between -0.44 and -0.277 values between -0.27 and -0.09231 values between -0.09 and 0.081400 values between 0.08 and 0.251309 values between 0.25 and 0.43673 values between 0.43 and 0.60207 values between 0.60 and 0.7733 values between 0.77 and 0.953 values between 0.95 and 1.121 values between 1.12 and 1.291 values between 1.98 and 2.161 values between 2.33 and 2.502 values between 2.85 and 3.021 values between 3.19 and 3.371 values between 3.37 and 3.54offnegativepositiveoften

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. Center
  2. thought
  3. ANNOT
  4. 缴纳
  5. 招待
  6. ỉ
  7. ENSION
  8. 元
  9. Imp

Suppresses

  1. alité
  2. [param
  3. yle
  4. Jays
  5. setMax
  6. ohana
  7. mour
  8. veal
  9. neau
  10. ToBounds