Neuron Explorer

Qwen3-0.6B

unclear: end-of-document markers

A neuron in layer 25 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 is hard to pin down. Its strongest moments are the hidden 'end of text' markers that separate web pages, plus a few odd spots in code and lists. Steering did not reveal a clear theme.

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

    technically clean, and is not actually any cleaner than a human mouth.⏎Is saliva of dog harmful?⏎Recent case reports demonstrate the harms of Capnocytophaga canimorsus bacteria in dog saliva, which can cause

  2. #2 peak

    is used to count the numbers of characters in⏎a string, as well as the number of characters in the string variable⏎>>> len("a string") 8 >>> >>> s = "a long string" >>> >>> len(s)

  3. #3 peak

    Sep 2012 • 1 answer⏎Posted 3 Oct 2014 • 1 answer<|endoftext|>Choosing Whole Foods for a Healthier You⏎Written by Eric DeAngelis,

  4. #4 peak

    considered a simple problem, one that a fifth grader may find in a math book. What about the problems we face in adulthood? (read more here)<|endoftext|>Задание от гостя:Размещено 13.

  5. #5 peak

    can safely remove.⏎But remember that you should never cut off more than two-thirds of a root at any time.⏎Also,<|endoftext|>Title VII makes sexual discrimination, i.e., using gender as a reason for making

  6. #6 peak

    , u, t)$.⏎<|endoftext|>While many students view summer as a time to forget about school, it remains an

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 more general term for a group of people who are themselves in their own interests and so are likely to favor their interests over other interests. What is the more general term for a group of people who are themselves in their own interests

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

    Show them your budget and let them be a part of some of the money decisions in your household. Seeing how money works can be a big tool for a tween.⏎#8. Know That You Are Their

  2. #2 peak

    in the field from August 2 – August 20.<|endoftext|>Genetics as it applies to evolution, molecular biology, and medical aspects.⏎10 posts • Page 1 of 1⏎Hope somebody can help, I've got an

  3. #3 peak

    JBS10AMA. To make a password even more secure, or applicable for services that require other characters, add special characters around it, like # JBS10AMA#.⏎Here are some

  4. #4 peak

    means that the files are stored in a compressed format.⏎For Python Implementation⏎You can use OpenCV to manipulate the images.⏎pip3 install opencv-python numpy⏎Open

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. L21:328 suppresses
  2. L22:259 excites
  3. L20:508 suppresses
  4. L8:51 suppresses
  5. L20:85 excites
  6. L21:341 excites
  7. L15:574 excites
  8. L22:2243 suppresses
  9. L20:843 suppresses
  10. L13:643 excites
  11. L3:38 suppresses
  12. L2:1499 suppresses
  13. L7:221 excites
  14. L16:496 weakly suppresses
  15. L19:389 weakly suppresses
  16. L10:754 weakly suppresses
  17. L0:2110 weakly excites
  18. L17:1837 weakly suppresses
  19. L20:213 weakly excites
  20. L19:439 weakly suppresses
  21. L4:243 weakly excites
  22. L5:2867 weakly suppresses
  23. L17:737 weakly suppresses
  24. L0:2476 weakly excites

Feeds later layers

  1. L26:855 strongly excites
  2. L27:952 strongly excites
  3. L27:1447 excites
  4. L26:612 suppresses end-of-text boundary tokens
  5. L27:619 suppresses
  6. L27:2159 excites
  7. L26:720 weakly suppresses 'New' in place names
  8. L27:865 weakly excites
  9. L27:614 weakly excites
  10. L27:1339 weakly excites
  11. L26:235 weakly suppresses
  12. L27:2277 weakly excites
  13. L26:611 weakly excites
  14. L27:2191 weakly suppresses
  15. L26:1072 weakly suppresses
  16. L27:2538 weakly suppresses
  17. L26:2218 weakly suppresses
  18. L27:1005 weakly excites
  19. L27:1848 weakly suppresses
  20. L26:2078 weakly suppresses
  21. L27:1456 weakly excites
  22. L27:2718 weakly suppresses
  23. L26:1391 weakly excites
  24. L26:609 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 -7.82 and -7.162 values between -4.49 and -3.823 values between -3.16 and -2.491 values between -2.49 and -1.8211 values between -1.82 and -1.16181 values between -1.16 and -0.493521 values between -0.49 and 0.18151 values between 0.18 and 0.8418 values between 0.84 and 1.513 values between 1.51 and 2.186 values between 2.18 and 2.841 values between 4.18 and 4.841 values between 6.18 and 6.841 values between 8.18 and 8.841 values between 9.51 and 10.181 values between 10.18 and 10.841 values between 12.18 and 12.841 values between 13.51 and 14.181 values between 14.84 and 15.511 values between 16.18 and 16.841 values between 18.18 and 18.84offnegativepositiveoften

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. #
  2. #
  3. #a
  4. #"
  5. ,#
  6. #\
  7. #,
  8. #=
  9. #",
  10. #g

Suppresses

  1. //⏎
  2. //
  3. //
  4. //⏎
  5. //(
  6. //"
  7. ////
  8. )//
  9. //'
  10. //"