Neuron Explorer

Qwen3-0.6B

dash starting a new list item

A neuron in layer 5 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 a dash that starts a new point in a list or a fresh item right after a line break. Its negative side is weaker and mostly fires on opening quotation marks. Turning it up did not produce an obvious change in the replies.

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

    -world problems involving geometric sequences.⏎Terms introduced in this lesson:⏎Teaching Strategies and Tips⏎Use this lesson to show how exponential functions and geometric sequences are related.⏎- In a geometric sequence, terms are found by multiplying the same constant to the previous

  2. #2 peak

    and silent killer. In the time it takes to do these simple tasks, a child can become submerged, loose consciousness, sustain permanent brain damage, or die.⏎- Get a towel (10 seconds)⏎- Answer the phone (2 minutes)⏎

  3. #3 peak

    = acceleration due to gravity⏎Since gravity is just an acceleration like any other, it can be used in any of the formulas that we have used so far.⏎- Just be careful about using the correct sign (positive or negative) depending on the

  4. #4 peak

    two.⏎Serious Causes of Eye Redness⏎Redness of eyes with pain, loss of vision, inflammation or thick discharge may necessitate an immediate treatment.⏎- Uveitis. This is the

  5. #5 peak

    atively.)⏎DiffuseThe adjective diffuse means spread out or not concentrated in one place. Diffuse can also be a verb meaning to circulate or to spread.⏎- She is the CEO of a large diffuse company. (Here, diffuse is an

  6. #6 peak

    likely will not notice anything odd when mites are at low populations; however, when they continue to grow to a high population you will start seeing the damage.⏎- Stippling of light dots on leaves⏎- Leaves turning yellow or reddish

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 know that the book is in the public domain. The user has no idea what's next. I'm not sure about the number of words. It's a book I'd like to be read by the people who are left in the

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

    gender-based violence, and challenging harmful stereotypes faced by people of all genders, we are creating a foundation for everyone to lead happier, healthier and more fulfilling lives.⏎“Like Canadians, our government believes that

  2. #2 peak

    Revolution, it easily identifies with the struggles and aspirations of working women everywhere. The figures represent women of different races and celebrate the contributions made by women throughout time.⏎“Women all over the world have one trait in common: they work, they work

  3. #3 peak

    .⏎“Particularly in low-income countries, exhausted health workers are battling to save lives in the midst of shortages of personal protective equipment, oxygen, and treatments.⏎“Vaccines have never been the way out of this crisis on their own,

  4. #4 peak

    , and to manipulate it. ... To arrange atoms into an ordered nanotechnology landscape of precisely spaced steps and terraces. ... To determine the size of an electrical current by tabulating, one by one,

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. L3:44 weakly suppresses
  2. L2:308 weakly suppresses
  3. L1:107 weakly suppresses
  4. L4:140 weakly suppresses
  5. L2:163 weakly excites
  6. L2:2396 weakly suppresses
  7. L4:231 weakly excites
  8. L1:1648 weakly excites
  9. L0:953 weakly suppresses
  10. L2:45 weakly excites
  11. L2:266 weakly suppresses
  12. L3:141 weakly excites
  13. L1:302 weakly suppresses
  14. L4:1175 weakly suppresses
  15. L3:1404 weakly excites
  16. L3:2208 weakly excites
  17. L4:1749 weakly excites
  18. L3:2567 weakly suppresses
  19. L2:329 weakly excites
  20. L3:1093 weakly suppresses
  21. L2:111 weakly suppresses
  22. L4:841 weakly suppresses
  23. L2:2550 weakly suppresses
  24. L3:145 weakly excites

Feeds later layers

  1. L6:172 suppresses
  2. L8:57 suppresses
  3. L10:801 excites
  4. L6:164 excites
  5. L6:1704 suppresses
  6. L7:1347 excites dash starting a new list item
  7. L7:237 suppresses
  8. L11:548 suppresses
  9. L8:2937 excites
  10. L17:84 excites
  11. L6:445 suppresses
  12. L12:1483 weakly excites
  13. L15:986 weakly suppresses
  14. L16:1389 weakly suppresses
  15. L16:300 weakly suppresses commas inside lists of nouns
  16. L13:371 weakly excites
  17. L8:299 weakly excites
  18. L8:131 weakly excites
  19. L7:25 weakly suppresses
  20. L8:739 weakly suppresses
  21. L15:215 weakly suppresses
  22. L12:399 weakly suppresses
  23. L24:1993 weakly suppresses
  24. L15:2287 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 -3.36 and -3.233 values between -2.01 and -1.881 values between -1.88 and -1.741 values between -1.74 and -1.612 values between -1.61 and -1.472 values between -1.47 and -1.342 values between -1.34 and -1.202 values between -1.20 and -1.073 values between -0.93 and -0.794 values between -0.79 and -0.6610 values between -0.66 and -0.5211 values between -0.52 and -0.3977 values between -0.39 and -0.25443 values between -0.25 and -0.121674 values between -0.12 and 0.021185 values between 0.02 and 0.15365 values between 0.15 and 0.2996 values between 0.29 and 0.4217 values between 0.42 and 0.562 values between 0.56 and 0.693 values between 0.69 and 0.832 values between 0.96 and 1.101 values between 1.64 and 1.771 values between 1.91 and 2.04offnegativepositiveoften

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. zman
  2. 也不例外
  3. arness
  4. sterol
  5. ETHER
  6. 局副局长
  7. erties
  8. acias
  9. 局局长
  10. passed

Suppresses

  1. urance
  2. 룸
  3. olo
  4. rowable
  5. hou
  6. odable
  7. nop
  8. oub
  9. ствие
  10. 问题是