Neuron Explorer

Qwen3-0.6B

end-of-text token after a document

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 reacts to the hidden marker the training data uses to separate one web page from the next, which shows up right where a document ends. Its strongest negative reactions are on a closing quotation mark followed by a comma. Steering had no clear visible effect.

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

    their . place. So, the students, teachers and other professionals finally had to resume their studies and jobs in government institutions like schools, colleges, courts etc.<|endoftext|>I hope you are all well and that you enjoyed some of your weekend in the

  2. #2 peak

    Hydrogen<|endoftext|>Educational Technology and Mobile Learning: 8 Excellent Augmented Reality Apps for iPad

  3. #3 peak

    management, risk management and time management skills.⏎- Software development in Java using various web-development technologies.⏎Figure 1: Traceability User Interface⏎Back to top<|endoftext|>William Gilly has seen a Kraken. The mythical squid beast with⏎ship

  4. #4 peak

    which can be physical or concepts, etc⏎Definitions of Rail:⏎Cambridge Dictionaries |⏎New Zealand |⏎Similar Words (using 'rail' as word stem):<|endoftext|>First Flag Flown⏎In 1960, when CDC moved from

  5. #5 peak

    Saturday<|endoftext|>15.1: The Science Fair (5 minutes)⏎The purpose of this

  6. #6 peak

    Rocky Mountains. OSC will continue to better understand wolverine behavior and advocate for increased local and national coordination.<|endoftext|>Regional Broadband Global Area Network (RBGAN)⏎Definition - What does Regional Broad

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 trying to understand the idea of a system, and I have been thinking about it. I have been thinking about it, and I have been trying, and I have been thinking about it. I have been thinking about it,

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

    ,” according to Currier.⏎Read the full article, Which States Have the Most Economic

  2. #2 peak

    ,” Dawson said. “Alltech’s distinct set of technologies can help in maintaining healthy

  3. #3 peak

    ,” we get the subject form (An Luan), and, by following genitive

  4. #4 peak

    ,” 05/31/2002, WGBH Media

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. L2:39 excites
  2. L2:54 excites
  3. L1:1929 weakly suppresses
  4. L1:110 weakly suppresses
  5. L1:2677 weakly suppresses
  6. L1:1321 weakly suppresses
  7. L2:1489 weakly suppresses
  8. L1:2480 weakly excites
  9. L25:478 weakly excites
  10. L2:46 weakly suppresses
  11. L10:371 weakly suppresses
  12. L2:60 weakly suppresses
  13. L2:212 weakly suppresses
  14. L9:623 weakly excites
  15. L2:128 weakly suppresses
  16. L1:37 weakly suppresses
  17. L4:239 weakly suppresses
  18. L2:55 weakly suppresses
  19. L1:2159 weakly suppresses
  20. L1:1262 weakly suppresses
  21. L1:868 weakly suppresses
  22. L14:1123 weakly suppresses
  23. L19:755 weakly suppresses
  24. L11:801 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.

2 values between -3.91 and -3.811 values between -1.70 and -1.601 values between -0.65 and -0.551 values between -0.55 and -0.4414 values between -0.34 and -0.23285 values between -0.23 and -0.131852 values between -0.13 and -0.021519 values between -0.02 and 0.08215 values between 0.08 and 0.1918 values between 0.19 and 0.29offnegativepositiveoften

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. 小
  2. présent
  3. ,label
  4. gis
  5. ,[
  6. 一个小
  7. Sm
  8. grim
  9. ogr
  10. uler

Suppresses

  1. impse
  2. 但这
  3. Paramount
  4. ))?
  5. NESS
  6. yet
  7. ariate
  8. surf
  9. обще
  10. 阗