Neuron Explorer

Qwen3-0.6B

dotted numbers and key parts

A neuron in layer 9 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron reacts to the dots and digits inside version numbers and IP-style addresses, like 22.214.171.124, and to the word "private" in talk about encryption keys. It goes strongly negative on words about password characters, such as "special" and "letters". Turning it up gave replies that were unrelated, so the link to its trigger is unclear.

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

    68k-palmos-coff-gcc -v should report its version number to be (at time of writing) 22.214.171.124-kgpd-07109

  2. #2 peak

    the for-mation of the dissimilar metal joint and the measurement of joint tensile strength⏎Welding Method 6, Paragraph 188.8.131.52 (Paraphrased, still in public

  3. #3 peak

    ated by Maria Ciaccio⏎©2018 Chicago Botanic Garden and my.chicagobotanic.org<|endoftext|>Hello. Sign In⏎Please enter a valid city, state or zip code⏎With the Food and Drug Administration (FDA

  4. #4 peak

    as being a List of Users.⏎Sometimes, it’s also handy to define a list of multiple Entities and Structures.⏎Until 184.108.40.2

  5. #5 peak

    uler or calipers with mm divisions⏎- Paper towel⏎- Microscope slide and cover slip⏎AQA: Topic 184.108.40.206 and 220.1<|endoftext|>Re export

  6. #6 peak

    , which specifies where the runtime can locate an assembly (for more information, see Specifying an Assembly's Location).⏎<codeBase version="188.8.131.52" href="http://www.litware

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 list of characters that contains a mix of numbers, symbols, and letters. This is a password... That's a password... that includes numbers, symbols, and letters. That's a password... that includes numbers, symbols,

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

    file represents a sequence of characters (letters, numbers or special characters) that are stored on a personal computer, accessible only to the PC owner

  2. #2 peak

    Even the simplest version is a fairly difficult password to crack. If you’re really security conscious you can make passwords stronger by:⏎- Use both upper and lower case letters⏎- Use more special characters⏎- Make the way you combine them more complicated

  3. #3 peak

    for Amazon, John Bob Smith could use 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

    ., Either-OR⏎The value has to be one of the following-⏎- Statment 1⏎- Statement 2⏎Regex for checking if its a valid Either of Two words i.e., Either-OR⏎Test string examples for the

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. L6:1361 suppresses
  2. L6:1307 weakly excites
  3. L5:2 weakly suppresses
  4. L8:5 weakly suppresses
  5. L8:1757 weakly suppresses
  6. L7:122 weakly excites
  7. L4:2725 weakly excites
  8. L0:279 weakly suppresses
  9. L7:174 weakly suppresses
  10. L6:7 weakly suppresses
  11. L7:2940 weakly excites
  12. L7:2605 weakly excites
  13. L0:2363 weakly suppresses
  14. L1:2725 weakly suppresses
  15. L4:2463 weakly excites
  16. L0:2528 weakly suppresses
  17. L6:2767 weakly excites
  18. L2:2827 weakly excites
  19. L8:632 weakly suppresses
  20. L2:2684 weakly suppresses
  21. L4:2004 weakly excites
  22. L8:12 weakly excites
  23. L7:2664 weakly suppresses
  24. L1:333 weakly suppresses

Feeds later layers

  1. L20:2760 suppresses
  2. L21:1220 suppresses
  3. L16:2197 suppresses
  4. L11:129 excites
  5. L15:352 weakly suppresses
  6. L10:628 weakly suppresses
  7. L21:2313 weakly excites
  8. L20:1577 weakly suppresses
  9. L11:1056 weakly suppresses
  10. L17:2246 weakly suppresses
  11. L14:1664 weakly suppresses
  12. L12:2967 weakly suppresses
  13. L22:1577 weakly excites
  14. L17:319 weakly excites
  15. L15:1910 weakly suppresses
  16. L10:2353 weakly suppresses
  17. L26:2934 weakly suppresses
  18. L27:2705 weakly suppresses
  19. L10:2551 weakly excites
  20. L17:2884 weakly suppresses
  21. L12:2303 weakly suppresses
  22. L20:2927 weakly suppresses
  23. L15:781 weakly suppresses
  24. L21:1383 weakly 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 -0.62 and -0.591 values between -0.53 and -0.503 values between -0.50 and -0.472 values between -0.47 and -0.441 values between -0.44 and -0.412 values between -0.41 and -0.383 values between -0.38 and -0.352 values between -0.35 and -0.325 values between -0.32 and -0.2911 values between -0.29 and -0.2624 values between -0.26 and -0.2332 values between -0.23 and -0.2062 values between -0.20 and -0.1771 values between -0.17 and -0.14132 values between -0.14 and -0.11196 values between -0.11 and -0.08286 values between -0.08 and -0.05367 values between -0.05 and -0.02496 values between -0.02 and 0.02420 values between 0.02 and 0.05376 values between 0.05 and 0.08332 values between 0.08 and 0.11257 values between 0.11 and 0.14207 values between 0.14 and 0.17154 values between 0.17 and 0.20135 values between 0.20 and 0.23108 values between 0.23 and 0.2660 values between 0.26 and 0.2950 values between 0.29 and 0.3243 values between 0.32 and 0.3527 values between 0.35 and 0.3816 values between 0.38 and 0.418 values between 0.41 and 0.447 values between 0.44 and 0.475 values between 0.47 and 0.501 values between 0.50 and 0.533 values between 0.53 and 0.562 values between 0.56 and 0.59offnegativepositiveoften

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. tribution
  2. 钊
  3. войны
  4. favor
  5. favor
  6. quarters
  7. _ctor
  8. cki
  9. 安置
  10. indifference

Suppresses

  1. validators
  2. validators
  3. validator
  4. 的男人
  5. validator
  6. ipa
  7. 合格
  8. 色情
  9. 手机号
  10. validate