Neuron Explorer

Qwen3-0.6B

email addresses at the end of text

A neuron in layer 3 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 spot inside an email address, right before the ".org" part, in example addresses like firstname.lastname@example.org. When it is turned up, the model's writing drifts into unrelated topics like lists, numbered quizzes and news stories.

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

    engineering disciplines in India. He has also authored multiple books on various areas of data science. He may be reached at email@example.com (preferred) or firstname.lastname@example.org .<|endoftext|>Recovery from Addiction⏎There can be many different pathways to rem

  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

    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

  4. #4 peak

    wide variety of languages, catering for beginning students to background speakers.⏎Our Faculty Members⏎Mr John Norberry: email@example.com⏎Mrs Laura Wade: firstname.lastname@example.org⏎Quite often as Language teachers, we are asked why students should have to

  5. #5 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

  6. #6 peak

    give you initial support and signpost you to appropriate help if required.⏎If you need help or have any questions about Mental Health First Aid please email: firstname.lastname@example.org or talk to your tutor.⏎Are you

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 most significant problem in the world? What is the most significant problem in the world? I think that it's possible to have a lot of people's questions, but I don't think that it's possible to have a lot

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

    s, families in the top 20 percent of income continued to see steady income gains, whiles families in the lower income brackets saw stagnant and/or falling incomes.⏎Why? Just

  2. #2 peak

    extent of the past forest line and the corresponding minimum shift in mean July temperatures, compared with the present.⏎The mean July temperatures in Finnish Lapland have been ca.⏎I have also had restricted access to my extensive holiday wardrobe, thanks to my pes

  3. #3 peak

    (London, 1900); Macallum, On the Detection and Localization of Phosphorus in Animal and Vegetable Cells, Proc. Roy.⏎A curious fact, which may be used for the detection of the minutest quantity of

  4. #4 peak

    , what types of cells they become, and how to control those complex mechanisms to facilitate development of new therapies.⏎Researchers a the Burnham Institute for Medical Research (Burnham) and The Scripps Research Institute

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. L2:2005 suppresses
  2. L2:237 excites
  3. L2:111 weakly suppresses
  4. L0:1301 weakly suppresses
  5. L1:1464 weakly excites
  6. L2:394 weakly excites '@example' in email addresses
  7. L2:424 weakly excites
  8. L2:2196 weakly excites
  9. L2:1321 weakly suppresses
  10. L2:70 weakly excites
  11. L0:512 weakly suppresses
  12. L2:122 weakly excites
  13. L2:49 weakly suppresses
  14. L1:1029 weakly excites
  15. L2:1710 weakly suppresses
  16. L0:178 weakly suppresses
  17. L2:45 weakly excites
  18. L2:1533 weakly excites
  19. L0:1224 weakly suppresses
  20. L2:527 weakly excites
  21. L1:146 weakly excites
  22. L1:2850 weakly suppresses
  23. L2:493 weakly suppresses
  24. L2:3070 weakly excites

Feeds later layers

  1. L4:89 strongly suppresses
  2. L8:1515 suppresses
  3. L4:1044 suppresses
  4. L4:1262 suppresses
  5. L8:1214 suppresses
  6. L15:2885 suppresses
  7. L10:258 suppresses
  8. L9:935 suppresses
  9. L4:735 suppresses
  10. L23:194 weakly suppresses
  11. L21:1150 weakly excites
  12. L4:675 weakly excites
  13. L5:2804 weakly suppresses
  14. L8:967 weakly suppresses
  15. L6:324 weakly suppresses
  16. L12:1435 weakly suppresses
  17. L12:2508 weakly suppresses
  18. L6:2644 weakly suppresses
  19. L24:96 weakly suppresses
  20. L5:381 weakly suppresses
  21. L10:762 weakly suppresses
  22. L16:2255 weakly suppresses
  23. L27:953 weakly suppresses
  24. L12:1746 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 -1.38 and -1.331 values between -0.88 and -0.831 values between -0.53 and -0.481 values between -0.48 and -0.432 values between -0.43 and -0.3811 values between -0.38 and -0.3316 values between -0.33 and -0.2828 values between -0.28 and -0.2365 values between -0.23 and -0.18149 values between -0.18 and -0.13291 values between -0.13 and -0.08531 values between -0.08 and -0.03843 values between -0.03 and 0.02734 values between 0.02 and 0.07525 values between 0.07 and 0.12338 values between 0.12 and 0.17203 values between 0.17 and 0.2290 values between 0.22 and 0.2738 values between 0.27 and 0.3224 values between 0.32 and 0.378 values between 0.37 and 0.424 values between 0.42 and 0.471 values between 0.47 and 0.522 values between 0.52 and 0.571 values between 0.57 and 0.62offnegativepositiveoften

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. erne
  2. #⏎⏎
  3. 寡
  4. orse
  5. /Gate
  6. ledge
  7. +⏎⏎
  8. (),⏎⏎
  9. 族自治县
  10. ",⏎⏎

Suppresses

  1. its
  2. itself
  3. ewan
  4. udiant
  5. ��作
  6. ��
  7. itin
  8. ifice
  9. tut
  10. ぶり