Neuron Explorer

Qwen3-0.6B

"way of" before life, looking, eating

A neuron in layer 6 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

The neuron lights up on the word "of" right after phrases like "way of", "ways of" or "mode of", where a noun like life, looking or eating is about to follow. When it is turned up, the model drifts into vague, abstract talk about "the world of being" and repeats "of" a lot. Turned down, it writes more concrete, everyday sentences.

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

    ahili is spoken by many.⏎Kenyan Tribes & People⏎Kenya is built on traditional tribal cultures and each tribe contributes to the unique lifestyle and way of life so many are intrigued by. There are 42 tribes across Kenya,

  2. #2 peak

    constitution (Article 2), Islam is the state religion. By the constitution's Article 31, it is the country's duty to foster the Islamic way of life. By Article 33, it is the country's duty to discourage

  3. #3 peak

    the one hand, given the scale and scope of the threats that they face with regard to climate change – including specific threats to their livelihoods, cultures and ways of life – their situation is different from that of other groups and from that of the

  4. #4 peak

    Mindset⏎One thing that should be stated is that inventors do not always think like the people who follow their inventions. They have their own mindset and way of looking at things. This should be obvious, because they are seeing *everything*

  5. #5 peak

    is packed with nutrients, light on calories, and high in fiber. In a nation known for massive portion sizes and ready access to highly processed foods, this way of eating should be a welcome change. But a closer looks reveals a more complicated,

  6. #6 peak

    th century. He also helped start the cognitive revolution in psychology through his review of B. F. Skinner's Verbal Behavior. He challenged the behaviorist way of looking at behavior and language. This was the main approach used in the 1

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 the history of the people in the area. The people will say that I have been thinking about the historical background of the area. I have been thinking about the past. This is a case where the people might be

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

    of government policy.⏎The goal is "to narrow as soon as possible the gap in economic development between Tibet and other areas of the nation" (White Paper on Tibet, Sep 1992). Chen Kuiyuan, a Chinese

  2. #2 peak

    by the Chinese. What was Tibet's homeland will become China's homeland. Beijing has finally admitted that the population transfer process goes on. (Third Work Forum on Tibet, July 1994). A wave of resettlement became apparent in

  3. #3 peak

    the locking up of perhaps 1 million Uyghurs, a mostly Muslim ethnic minority, in China’s at times violence-torn far western region of Xinjiang.⏎All anniversaries in China are sensitive, with the party eager to control

  4. #4 peak

    (International Campaign for Tibet 2/11/94). These settlers recieve subsidies and other

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. L3:1537 weakly excites
  2. L4:37 weakly suppresses
  3. L3:2987 weakly excites
  4. L1:2612 weakly excites
  5. L3:2721 weakly excites
  6. L5:2117 weakly excites
  7. L4:2699 weakly excites
  8. L5:2061 weakly excites
  9. L2:1660 weakly excites
  10. L3:2886 weakly suppresses
  11. L4:144 weakly excites
  12. L1:979 weakly suppresses
  13. L4:3047 weakly excites
  14. L4:1537 weakly excites
  15. L4:1498 weakly excites
  16. L3:885 weakly suppresses
  17. L1:2041 weakly excites
  18. L0:2963 weakly excites
  19. L4:1110 weakly excites
  20. L4:784 weakly suppresses
  21. L4:159 weakly excites
  22. L3:3054 weakly excites
  23. L3:692 weakly excites
  24. L2:1523 weakly suppresses

Feeds later layers

  1. L8:202 excites
  2. L7:2795 suppresses
  3. L11:1392 weakly excites 'of' in fixed technical phrases
  4. L23:2213 weakly suppresses
  5. L10:56 weakly suppresses
  6. L10:1836 weakly suppresses
  7. L7:2607 weakly excites
  8. L17:1015 weakly excites
  9. L25:1753 weakly suppresses
  10. L26:2257 weakly suppresses
  11. L13:1335 weakly excites 'of' inside fixed noun phrases
  12. L23:647 weakly suppresses
  13. L22:2130 weakly excites
  14. L15:2276 weakly suppresses
  15. L9:849 weakly suppresses
  16. L25:968 weakly excites
  17. L24:1382 weakly excites
  18. L18:43 weakly excites
  19. L10:239 weakly excites
  20. L22:1148 weakly suppresses
  21. L14:2397 weakly suppresses
  22. L21:131 weakly excites
  23. L17:1771 weakly excites
  24. L9:116 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 -6.81 and -6.611 values between -2.12 and -1.921 values between -1.92 and -1.721 values between -1.51 and -1.314 values between -1.11 and -0.901 values between -0.90 and -0.706 values between -0.70 and -0.49155 values between -0.49 and -0.291043 values between -0.29 and -0.092222 values between -0.09 and 0.12416 values between 0.12 and 0.3240 values between 0.32 and 0.5311 values between 0.53 and 0.734 values between 0.73 and 0.932 values between 1.14 and 1.34offnegativepositiveoften

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. loom
  2. Document
  3. 舸
  4. ownership
  5. �
  6. كوك
  7. motors
  8. TokenType
  9. fen
  10. หมาย

Suppresses

  1. 浴室
  2. arie
  3. остоя
  4. 因地
  5. urface
  6. 这种事情
  7. icina
  8. uffer
  9. handling
  10. пров