Neuron Explorer

Qwen3-0.6B

"some" in "some kind" and "at some point"

A neuron in layer 20 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 word "some" when it means an unspecified amount or kind, such as "some kind of", "at some point" or "in some way". Turned up, the model kept producing "some kind of some sort of".

Written by Claude from this neuron's activations and steering outputs. Confidence: high. 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

    protein production, they still involve proteins. So is it safe to say that while RNA performs several functions in the cell, all of them are related to proteins in some way? I might have answered

  2. #2 peak

    when you actually do well and are responsible in school.⏎Things you may find useful to stay focused:⏎- Computer with word processor or spreadsheet program⏎- Planner of some kind⏎- Goals sheet⏎- Cell phone or some kind of alarm reminder⏎

  3. #3 peak

    out of 100. Which may not sound like much.⏎But consider that 1 out of 15,000 kids gets cancer of some kind, and think about the attention and research and money devoted to understanding and treating

  4. #4 peak

    . Here are two important reasons why:⏎The odds of needing long-term care are high:⏎- Approximately 70% of people will need long-term care at some point during their lifetimes after reaching age 65.*⏎- Approximately 8

  5. #5 peak

    As<|endoftext|>How to Write a Research Paper. Whether you're in a history, literature, or science class, you'll probably have to write a research paper at some point. It may seem daunting when you're just starting out

  6. #6 peak

    Because of this, the sun will lose its brightness, becoming black for summers hereafter" (LXXXI.2). This may refer to an eclipse of some sort, or perhaps even a complete breakdown of our stratosphere, the skies

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 more that a company can use a lot of its resources, the more it can afford to take a larger and larger amount of a single, specific and very specific, and therefore, the more it can afford a smaller and more specific,

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

    AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file

  2. #2 peak

    c.⏎For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Michael McNulty)⏎If references are entirely missing, you can add them using this form.<|endoftext|>Farmers

  3. #3 peak

    egg.⏎If you are reading this message, Please click this link to reload this page.(Do not use your browser's "Refresh" button). Please email us if you're running the latest version of your browser and you still see this message.⏎

  4. #4 peak

    second session through Eventbrite as well, if you are interested in attending both: https://scisatadapt2.eventbrite.ca⏎Please contact us if you have any questions & we hope to see you there!<|endoftext|>Last week a

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. L17:2579 suppresses
  2. L18:1920 suppresses
  3. L19:2274 excites
  4. L15:1828 suppresses
  5. L18:2820 excites
  6. L15:976 suppresses
  7. L13:1730 suppresses
  8. L14:1107 suppresses
  9. L13:1051 excites
  10. L19:289 excites
  11. L17:2219 suppresses
  12. L15:3059 suppresses 'and' or 'or' joining the last list items
  13. L16:730 excites
  14. L10:2898 suppresses
  15. L17:2396 suppresses
  16. L18:2960 excites
  17. L12:3054 suppresses
  18. L13:1990 weakly suppresses
  19. L11:679 weakly excites
  20. L14:2571 weakly suppresses
  21. L15:2322 weakly excites
  22. L7:1729 weakly excites
  23. L12:886 weakly excites
  24. L6:16 weakly excites

Feeds later layers

  1. L27:1124 strongly excites
  2. L22:926 strongly excites
  3. L23:2246 excites
  4. L21:2124 excites
  5. L22:2836 excites
  6. L24:823 excites
  7. L26:677 excites
  8. L23:2193 excites
  9. L21:1725 weakly excites
  10. L23:2536 weakly excites
  11. L25:871 weakly excites
  12. L25:2301 weakly excites
  13. L23:2339 weakly excites
  14. L27:1593 weakly suppresses
  15. L21:2585 weakly excites
  16. L21:2859 weakly excites
  17. L25:1588 weakly suppresses
  18. L21:2515 weakly excites
  19. L24:1078 weakly excites
  20. L26:434 weakly excites
  21. L21:913 weakly suppresses
  22. L21:547 weakly excites
  23. L27:1069 weakly suppresses
  24. L21:1705 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.

6 values between -2.31 and -1.9735 values between -1.97 and -1.64139 values between -1.64 and -1.30383 values between -1.30 and -0.97799 values between -0.97 and -0.631284 values between -0.63 and -0.301055 values between -0.30 and 0.04117 values between 0.04 and 0.3731 values between 0.37 and 0.718 values between 0.71 and 1.0410 values between 1.04 and 1.377 values between 1.37 and 1.712 values between 1.71 and 2.044 values between 2.04 and 2.383 values between 2.38 and 2.714 values between 2.71 and 3.053 values between 3.05 and 3.382 values between 3.72 and 4.052 values between 4.39 and 4.722 values between 4.72 and 5.062 values between 5.06 and 5.392 values between 5.39 and 5.721 values between 5.72 and 6.062 values between 7.40 and 7.732 values between 9.07 and 9.411 values between 9.41 and 9.742 values between 10.74 and 11.08offnegativepositiveoften

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. some
  2. some
  3. Some
  4. Some
  5. somehow
  6. 某种
  7. somewhere
  8. 一些
  9. somew
  10. SOME

Suppresses

  1. 率达
  2. ::__
  3. 度过
  4. amment
  5. 情况下
  6. unct
  7. 及以上
  8. двига
  9. .defaultProps
  10. .AnchorStyles