Neuron Explorer

Qwen3-0.6B

scope words like all, many, suitable

A neuron in layer 14 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on words that describe how much or how widely something applies, such as 'all', 'many', 'across' and 'suitable'. Turning it up made the model repeat phrases about time and things without a clear point.

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

    which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.<|endoftext|>- Major Systems >⏎- The Plumbing Rough-In⏎The Plumbing Rough

  2. #2 peak

    lots of secrets.⏎- Because others are either sleeping or already have mates.⏎- Basic instincts.⏎- To get into the lime-light.⏎- In pursuit of a suitable alliance.⏎

  3. #3 peak

    on health expenditure and quality of care, building on the OECD expertise in these areas. Each indicator is presented in a user-friendly format, consisting of charts illustrating variations across countries and over time, a brief descriptive analysis highlighting the major findings conveyed by the

  4. #4 peak

    up to 10 minutes with each feeding...One bed bug will usually take more than one bite. Once a bed bug inserts its mouthparts and finds a suitable blood vessel, it will begin feeding. ~ source⏎While bed bugs like to

  5. #5 peak

    more than others.⏎Baits need to be specific to the catch you’re trying to make. Not all baits can be used for all types of fish. To put things into perspective, catfish love raw chicken liver

  6. #6 peak

    - Lessons align with National Health Education standards⏎- Lessons align with SEL programming and competency areas⏎Purchase grants one user, individual use of course materials for a self-selected period from date of purchase. This contract is extendable. Multi-year discounts available

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 story of the human race, as it exists in the heart of the novel. The story of the human existence on Earth, as a person. " " " " " " " " " " " " " " " " "

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

    enhance public safety, and provides lifelong learning and technical exchange opportunities benefiting the global engineering and technology community. ASME has more than 127,000 members worldwide.⏎ASME′S VISION, MISSION STATEMENT AND CORE

  2. #2 peak

    .⏎Largest Cities in West Virginia⏎West Virginia is one of the few US states not to have a city with more than 100,000 residents. In fact, the largest city in the state, Charleston (the state

  3. #3 peak

    6, our organization in Chicago was called upon to assemble some detailed cost figures from butter manufacturers whose 77 plants produced almost 150,000,000 pounds of butter annually. These figures reflected accurately the big increases

  4. #4 peak

    and an astute political observer who, while she lived, played a key role in advancing her husband’s career.⏎Like us on Facebook and get articles directly in your news feed<|endoftext|>To Colored Men!⏎This poster was used to recruit recently freed

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. L5:1072 suppresses
  2. L10:167 suppresses
  3. L12:2802 excites
  4. L12:2841 excites
  5. L12:1531 excites
  6. L13:595 weakly excites
  7. L11:2630 weakly suppresses weak 'for' and 'all' quantifier signal, unclear
  8. L6:826 weakly excites
  9. L13:851 weakly suppresses
  10. L9:278 weakly suppresses
  11. L11:1174 weakly suppresses
  12. L7:716 weakly suppresses
  13. L3:2571 weakly excites
  14. L1:629 weakly excites 'across' meaning spread over an area
  15. L4:918 weakly excites
  16. L4:1843 weakly excites
  17. L10:1697 weakly excites
  18. L12:1809 weakly excites
  19. L7:2758 weakly excites
  20. L11:918 weakly suppresses
  21. L4:2902 weakly excites
  22. L10:1683 weakly excites
  23. L10:875 weakly suppresses
  24. L9:1824 weakly excites

Feeds later layers

  1. L19:1854 excites
  2. L19:1833 excites
  3. L17:2388 excites
  4. L21:1486 excites
  5. L15:1019 excites
  6. L18:77 excites
  7. L16:1009 excites
  8. L19:2132 excites
  9. L17:1979 excites
  10. L19:1668 excites
  11. L15:1507 excites
  12. L16:982 weakly excites
  13. L15:428 weakly excites
  14. L15:2850 weakly excites
  15. L22:529 weakly excites
  16. L15:1840 weakly excites
  17. L16:1122 weakly excites
  18. L16:2556 weakly excites
  19. L18:2465 weakly excites
  20. L27:1170 weakly suppresses
  21. L15:2672 weakly excites
  22. L18:2058 weakly excites
  23. L18:309 weakly excites
  24. L21:808 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 -2.39 and -2.251 values between -2.25 and -2.121 values between -1.73 and -1.602 values between -1.46 and -1.332 values between -1.33 and -1.202 values between -1.20 and -1.073 values between -1.07 and -0.9410 values between -0.94 and -0.8010 values between -0.80 and -0.6711 values between -0.67 and -0.5418 values between -0.54 and -0.4164 values between -0.41 and -0.28249 values between -0.28 and -0.151060 values between -0.15 and -0.011551 values between -0.01 and 0.12645 values between 0.12 and 0.25194 values between 0.25 and 0.3855 values between 0.38 and 0.5111 values between 0.51 and 0.646 values between 0.64 and 0.783 values between 0.78 and 0.912 values between 0.91 and 1.041 values between 1.43 and 1.573 values between 1.70 and 1.831 values between 1.96 and 2.091 values between 2.09 and 2.221 values between 2.75 and 2.88offnegativepositiveoften

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. taxing
  2. Inflater
  3. ief
  4. 阵阵
  5. égor
  6. afi
  7. isky
  8. syn
  9. aise
  10. ỹ

Suppresses

  1. icles
  2. وص
  3. culos
  4. itations
  5. culo
  6. straints
  7. cord
  8. �자
  9. писан
  10. ulas