Neuron Explorer

Qwen3-0.6B

'of' after all, each, or any

A neuron in layer 20 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 lights up on the word 'of' when it follows words like 'all', 'each' or 'any two', as in 'All of these cases'. When it was turned up, the model's replies did not show a clear theme, so the link to the text is only seen in the examples.

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

    the most important factor in determining how a person came to use one style or another in their most intimate relationships, namely with their families, is through learning.⏎All of the styles of anger management are learned styles. Consequently, if they were learned,

  2. #2 peak

    some individuals, which may be greater than another’s needs. Further, the absence of certain diseases does not indicate that a person is meeting their nutrient needs.⏎Each of us fits into one of these categories:⏎- You are deficient in one or more

  3. #3 peak

    best by hearing their instructor explain it. Some favor learning it from the textbook. Others need to play with specimens in the lab to really "get it."⏎All of these differences in learning among individuals are often called their "learning styles." There are

  4. #4 peak

    drugs, devices, and procedures. "Certain trends are increasing longevity and others are reducing it," he says. "I'm trying to figure out how much each of these trends contributes."⏎Over the period Lichtenberg studied a huge number of

  5. #5 peak

    by , which in turn join to form . These drain into ducts situated between the lobes of the gland (called or excretory ducts).⏎All of the human salivary glands terminate in the mouth, where the saliva proceeds to

  6. #6 peak

    two end systems⏎B. It specifies the quality of the data & connection⏎C. It specify the size of data⏎D. All of the above⏎6-4. The class-based addressing is also known as⏎

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: each each each, each each, each each, each each, each each, each each, each each, each each, each each, each each, each each, each each, each each, each each, each each, each each

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

    and replace them when necessary. This guide provides a comprehensive look into the world of HVAC parts.⏎Understanding Different HVAC Components⏎HVAC systems consist of several key components, each with a specific function. The furnace is responsible for heating air, the air

  2. #2 peak

    fractive processor in the hands of the very type of machine learning system it's designed to accelerate.⏎The resulting processor is made up of multiple diffractive layers, made up of passive materials that allow the transmission of light. Information is encoded as

  3. #3 peak

    millions of people worldwide. It is characterized by the abnormal growth of cells in the body, which can invade and destroy surrounding tissues. There are various types of cancer, each with its own unique characteristics and treatment options. In this article, we will

  4. #4 peak

    Dry Eye” is a term used to describe a group of conditions that cause irritation and damage to the ocular surface. There are many different forms of dry eye, each with a unique cause, and each with a unique set of treatment options available

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. L19:1837 excites
  2. L16:1718 suppresses
  3. L19:2285 suppresses
  4. L17:2291 excites
  5. L19:2445 excites
  6. L16:1418 excites
  7. L19:2682 excites
  8. L17:1583 excites
  9. L14:2704 suppresses
  10. L19:1422 excites
  11. L15:1245 excites
  12. L17:2808 excites
  13. L18:212 excites
  14. L16:1317 weakly excites
  15. L16:1955 weakly suppresses
  16. L15:275 weakly suppresses
  17. L15:1679 weakly excites
  18. L18:525 weakly excites
  19. L15:2998 weakly suppresses
  20. L18:2661 weakly suppresses
  21. L8:467 weakly excites
  22. L4:450 weakly excites
  23. L12:1088 weakly suppresses
  24. L11:272 weakly suppresses

Feeds later layers

  1. L27:1187 strongly suppresses
  2. L24:1149 strongly suppresses
  3. L26:890 strongly suppresses
  4. L22:477 strongly suppresses
  5. L23:1305 suppresses
  6. L23:1807 suppresses
  7. L22:505 suppresses
  8. L21:1884 suppresses
  9. L21:1446 suppresses
  10. L23:485 suppresses
  11. L22:940 suppresses
  12. L23:1240 suppresses
  13. L23:96 excites
  14. L21:744 suppresses
  15. L27:769 suppresses
  16. L25:1394 suppresses
  17. L23:402 excites
  18. L21:1983 suppresses
  19. L25:1720 weakly suppresses
  20. L24:3021 weakly suppresses
  21. L26:917 weakly suppresses
  22. L21:2646 weakly suppresses
  23. L22:1633 weakly suppresses
  24. L21:840 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 -11.70 and -10.951 values between -10.95 and -10.201 values between -10.20 and -9.451 values between -7.94 and -7.193 values between -6.44 and -5.681 values between -5.68 and -4.931 values between -4.93 and -4.184 values between -4.18 and -3.433 values between -3.43 and -2.6812 values between -2.68 and -1.9237 values between -1.92 and -1.17461 values between -1.17 and -0.422581 values between -0.42 and 0.33748 values between 0.33 and 1.0930 values between 1.09 and 1.8410 values between 1.84 and 2.596 values between 2.59 and 3.342 values between 3.34 and 4.102 values between 5.60 and 6.351 values between 13.88 and 14.631 values between 15.38 and 16.131 values between 17.64 and 18.39offnegativepositiveoften

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. 在内的
  2. 粕
  3. hunter
  4. ACCEPT
  5. uru
  6. ati
  7. skip
  8. tics
  9. aze
  10. igator

Suppresses

  1. each
  2. each
  3. 每个
  4. Each
  5. Each
  6. EACH
  7. 每個
  8. _each
  9. 每位
  10. 每一个