Neuron Explorer

Qwen3-0.6B

placeholder example email domain

A neuron in layer 1 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 '@example' part of made-up email addresses like 'firstname.lastname@example.org'. Its strongest negative reactions are on 'art' in phrases like 'state of the art', which is a different pattern. Turning it up did not produce text about email or contact details.

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

    the Department of Construction, Chaoyang University of Technology, Taichung 41349, Taiwan (e-mail: firstname.lastname@example.org).⏎Cite:Ming-Ju Lee, Ming-Gin Lee, Y

  2. #2 peak

    of Construction, Chaoyang University of Technology, Taichung 41349, Taiwan (corresponding author's e-mail: firstname.lastname@example.org, email@example.com).⏎Chia-Liang Chiang is with

  3. #3 peak

    version be performed in public only once; if interested in presenting a realization of the A.N.L. - folds, please contact Sever Tipei (firstname.lastname@example.org) to obtain a personal version.⏎Five variants of the ANL-folds

  4. #4 peak

    : Czech Centre for Science and Society⏎Contact person: RNDr. Karel Charvát, firstname.lastname@example.org⏎Visit Inspire4Youth’s NEW Facebook page!⏎Open INSPI

  5. #5 peak

    the publication for benchmarking.⏎To explore opportunities for collaboration with subject-matter experts on your assessment and evaluation efforts, contact PRA Well-Being at firstname.lastname@example.org.⏎This resource was first shared in 2019.<|endoftext|>Social

  6. #6 peak

    how your school can get involved with Bush Builders contact firstname.lastname@example.org⏎Brothers Island tuatara⏎For just over six years, Wellington

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 main idea. This is a possible way to think about the problem. This is a possible way to think about the problem. I will now present the key results. This is a possible way to think about the problem. This is a

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

    determine the three dimensional structure and function of biomolecules at atomic resolution. This is significantly important for researching the basic components of life and understanding illnesses. State of the art experimental stations for serial femtosecond crystallography offer the opportunity to

  2. #2 peak

    0 days – nearly twice the duration achieved by state-of-the-art NASA balloons. “Even three weeks is very rare,” Lindstrand scoffed.⏎

  3. #3 peak

    for electric vehicles is still a work in progress however. The first genuine electric motor was produced as early as 1834. Today, state-of-the-art, innovative technologies are still based on discoveries made by researchers nearly<|endoftext|>The material in

  4. #4 peak

    was made primarily for use in calculators . By today's standards, this microprocessor would widely be considered inadequate, but at the time it was state-of-the-art. The 4-bit processor was made up of 2,<|endoftext|>The European

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. L0:1224 suppresses
  2. L0:178 suppresses
  3. L0:1301 suppresses
  4. L0:893 weakly excites
  5. L0:34 weakly excites
  6. L0:1150 weakly suppresses
  7. L0:281 weakly excites
  8. L0:166 weakly suppresses
  9. L0:2074 weakly suppresses
  10. L0:420 weakly excites
  11. L0:2962 weakly excites
  12. L0:1807 weakly suppresses
  13. L0:1633 weakly excites
  14. L0:262 weakly excites
  15. L0:1063 weakly suppresses
  16. L0:1404 weakly excites
  17. L0:1626 weakly suppresses
  18. L0:378 weakly excites
  19. L0:2745 weakly excites
  20. L0:1818 weakly suppresses
  21. L0:1266 weakly excites
  22. L0:691 weakly suppresses
  23. L0:1153 weakly excites
  24. L0:1190 weakly excites

Feeds later layers

  1. L14:2170 weakly suppresses
  2. L22:990 weakly suppresses
  3. L11:1729 weakly suppresses
  4. L12:466 weakly excites
  5. L15:544 weakly excites
  6. L5:2826 weakly suppresses
  7. L8:327 weakly suppresses
  8. L3:200 weakly suppresses comma after a finished clause
  9. L16:1057 weakly excites
  10. L24:581 weakly suppresses
  11. L14:1890 weakly excites
  12. L23:1411 weakly excites
  13. L7:1392 weakly suppresses
  14. L18:2119 weakly suppresses
  15. L2:1032 weakly excites
  16. L13:2523 weakly suppresses
  17. L23:1081 weakly suppresses
  18. L27:61 weakly excites
  19. L22:664 weakly suppresses
  20. L18:1286 weakly suppresses
  21. L2:1040 weakly suppresses
  22. L21:2289 weakly suppresses
  23. L9:1013 weakly excites
  24. L8:1568 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 -0.90 and -0.852 values between -0.65 and -0.611 values between -0.41 and -0.365 values between -0.36 and -0.316 values between -0.31 and -0.269 values between -0.26 and -0.2154 values between -0.21 and -0.16161 values between -0.16 and -0.11361 values between -0.11 and -0.07904 values between -0.07 and -0.021439 values between -0.02 and 0.03517 values between 0.03 and 0.08232 values between 0.08 and 0.13118 values between 0.13 and 0.1853 values between 0.18 and 0.2329 values between 0.23 and 0.2811 values between 0.28 and 0.333 values between 0.33 and 0.381 values between 0.43 and 0.481 values between 1.02 and 1.06offnegativepositiveoften

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. 党的领导
  2. 度过
  3. idente
  4. pains
  5. 筋
  6. 스트
  7. .ByteString
  8. 主义思想
  9. _MetadataUsageId
  10. 济

Suppresses

  1. itionally
  2. bard
  3. ories
  4. ourd
  5. ллер
  6. 婵
  7. ulu
  8. rema
  9. вел
  10. ceu