Neuron Explorer

Qwen3-0.6B

period closing a web blurb

A neuron in layer 22 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 on the full stop that ends a closing sentence in web page boilerplate, such as a medical disclaimer, a call to contact someone, or a promotional line, often just before a new unrelated article starts. Turning it up did not make the writing show a clear 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

    not intended to be a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of qualified health providers with questions you may have regarding medical conditions.<|endoftext|>The Amendment Process and the African American Fight for Representation and Equality⏎Black History

  2. #2 peak

    for your stargazing needs. Let’s dive in!⏎What is the aperture of a telescope?⏎By definition,

  3. #3 peak

    bodies, and pigment granules. Understanding these components will not only deepen your knowledge of hair but also help you identify them and comprehend their significance. So, let's dive in!⏎The cuticle is the outermost layer of

  4. #4 peak

    access to this title, please contact your librarian.⏎To troubleshoot, please check our FAQs, and if you can't find the answer there, please contact us.<|endoftext|>Indigenous Peoples and Climate Change: from victims to change agents through decent work

  5. #5 peak

    can also visit the Gambling Help Online website here.⏎If you would like to read more about Anastasia’s research, you can read her article in The Conversation here.<|endoftext|>Continued from Part 1...⏎With the advent of this international distribution of

  6. #6 peak

    return to a shielded base.⏎To continue reading this article, subscribe to receive access to all of newscientist.com, including 20 years of archive content.<|endoftext|>Fly Created To Study How A Normal Cell Turns Cancerous⏎The study

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 first. Core. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

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

    , we are printing the element for index i and decrementing the value of i by 1.⏎If you run this program, it will print the below output:⏎5 4 3 2 1⏎We need to use the range

  2. #2 peak

    heading), the complete sequence is:⏎<H1>This is the Page Heading</H1>A break between paragraphs is den

  3. #3 peak

    most illuminating being the incandescent electric bulb, the phonograph and the motion-picture projector. Who was he?⏎- Match the following with their inventors:⏎(a

  4. #4 peak

    (too tired to check who it was that posted it, and I can't see just now anyway :P)⏎void genFactorial(int x, int t)⏎int total = t; // you probably wouldn't even need total now⏎void

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. L20:44 strongly excites
  2. L20:46 strongly excites
  3. L17:1523 suppresses
  4. L18:2322 suppresses end-of-text token after a finished passage
  5. L21:619 suppresses
  6. L16:397 suppresses
  7. L17:1088 excites
  8. L15:774 excites
  9. L17:1029 excites
  10. L16:2510 excites
  11. L16:235 suppresses
  12. L20:460 excites
  13. L17:658 suppresses
  14. L17:2723 excites
  15. L14:667 suppresses
  16. L21:100 excites
  17. L21:660 excites
  18. L17:68 suppresses
  19. L15:101 excites
  20. L21:759 excites
  21. L16:3064 excites
  22. L17:135 suppresses
  23. L14:2826 excites
  24. L18:926 excites

Feeds later layers

  1. L24:211 strongly suppresses
  2. L26:449 strongly suppresses
  3. L25:397 strongly excites
  4. L27:891 strongly suppresses
  5. L25:808 strongly excites
  6. L26:864 strongly excites
  7. L24:11 excites
  8. L24:736 excites
  9. L26:775 excites
  10. L27:975 excites
  11. L27:204 suppresses
  12. L23:100 suppresses comma or full stop ending a clause
  13. L26:373 suppresses
  14. L27:366 excites
  15. L25:940 suppresses
  16. L26:828 suppresses
  17. L26:993 suppresses
  18. L25:131 suppresses
  19. L27:569 excites
  20. L27:116 excites
  21. L26:230 excites
  22. L26:34 suppresses
  23. L27:467 excites
  24. L27:2391 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 -5.04 and -4.451 values between -4.45 and -3.872 values between -3.87 and -3.282 values between -3.28 and -2.705 values between -2.70 and -2.1110 values between -2.11 and -1.5326 values between -1.53 and -0.9488 values between -0.94 and -0.362174 values between -0.36 and 0.231545 values between 0.23 and 0.8142 values between 0.81 and 1.405 values between 1.40 and 1.993 values between 1.99 and 2.571 values between 2.57 and 3.161 values between 3.16 and 3.741 values between 8.42 and 9.011 values between 17.79 and 18.38offnegativepositiveoften

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. <|endoftext|>
  2. .
  3. 。
  4. .?
  5. %;">
  6. ?
  7. ```
  8. .]
  9. ;">
  10. .)

Suppresses

  1. ').⏎
  2. ").⏎
  3. ',)⏎
  4. ’.⏎⏎
  5. '.⏎
  6. ''}⏎
  7. ""}⏎
  8. ".⏎
  9. `.⏎
  10. '))⏎