Neuron Explorer

Qwen3-0.6B

abbreviation periods after initials

A neuron in layer 0 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 full stop or comma that comes right after a short abbreviation or a single initial, like 'M.' in a name or 'U.S.' or 'D.C.'. When it is turned up, the model's writing drifted into rambling and odd phrasing, with no clear theme.

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

    that threatens the sustainability and resilience of our fishing communities,<|endoftext|>Suicide and Social Change in China⏎- Cite this article as:⏎- Phillips, M.R., Liu, H. & Zhang, Y. Cult Med Psychiatry (199

  2. #2 peak

    ., Swarup R., Tassinari A., Pandey B.K., York L.M., Atkinson B.S., Sturrock C.J., Mooney S.J., Hochholdinger F.,

  3. #3 peak

    the Western states? Does Nevada have a surplus?⏎Mike Cox, big game biologist, Nevada Department of Wildlife<|endoftext|>|Written by health professionals: Doctor, M.D., CphT, and others - but easy to read.|⏎METABOL

  4. #4 peak

    Bovina R., Pattem J.K., Borkar A.N., Lombardi M., Forestan C., Milner S.G., Davis J.L., Lale A., Kirschner G.K

  5. #5 peak

    .D., assistant professor of psychology in the School of Science at Indiana University-Purdue University

  6. #6 peak

    influence of aerosols on the global climate.⏎Ault, A.P., et al. “Raman Microspectroscopy and Vibrational Sum Frequency Generation

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 been thinking about lately. I have been thinking about lately. I have been thinking about lately. I have been thinking about lately. I have been thinking about lately. I have been thinking about lately. I have been thinking about lately

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

    or ‘auspicious’ (cf. Nandi verses in Sanskrit drama). Nandi is the name of Lord S

  2. #2 peak

    ada (c. 1475 or 1486 – between 15

  3. #3 peak

    period. We used repeated-state (i.e. abundance trends) and rate (i.e. colonization and persistence) responses to advance

  4. #4 peak

    cf. canguzua [In] Sea Slug Forum. Australian Museum, Sydney.

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

None: this is the first layer.

Feeds later layers

  1. L3:1224 excites
  2. L1:1925 suppresses
  3. L5:896 excites
  4. L2:1830 excites
  5. L3:1784 weakly excites
  6. L8:854 weakly excites
  7. L9:332 weakly excites
  8. L3:2089 weakly excites
  9. L21:1255 weakly suppresses
  10. L15:288 weakly excites
  11. L26:2577 weakly suppresses
  12. L5:456 weakly suppresses
  13. L2:2214 weakly excites
  14. L8:1131 weakly excites "your" addressing the reader
  15. L12:1093 weakly excites
  16. L9:1176 weakly suppresses
  17. L2:338 weakly excites
  18. L18:2478 weakly excites
  19. L8:1219 weakly suppresses
  20. L19:2792 weakly excites
  21. L6:58 weakly excites
  22. L24:102 weakly excites
  23. L10:2317 weakly excites
  24. L4:662 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 -0.42 and -0.383 values between -0.31 and -0.274 values between -0.27 and -0.246 values between -0.24 and -0.2020 values between -0.20 and -0.1654 values between -0.16 and -0.13130 values between -0.13 and -0.09319 values between -0.09 and -0.05772 values between -0.05 and -0.021286 values between -0.02 and 0.02739 values between 0.02 and 0.06338 values between 0.06 and 0.09136 values between 0.09 and 0.1352 values between 0.13 and 0.1715 values between 0.17 and 0.2012 values between 0.20 and 0.243 values between 0.24 and 0.283 values between 0.28 and 0.311 values between 0.31 and 0.351 values between 0.35 and 0.391 values between 0.39 and 0.422 values between 0.42 and 0.462 values between 0.50 and 0.532 values between 0.53 and 0.571 values between 0.61 and 0.641 values between 0.64 and 0.681 values between 0.72 and 0.751 values between 0.75 and 0.791 values between 0.86 and 0.901 values between 1.01 and 1.05offnegativepositiveoften

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. bles
  4. '?
  5. ус
  6. "?
  7. >
  8. acon
  9. -validator
  10. лей

Suppresses

  1. riday
  2. Perc
  3. getEmail
  4. getCell
  5. 一手
  6. ordova
  7. imeline
  8. iskey
  9. 客气
  10. umblr