Neuron Explorer

Qwen3-0.6B

'of' inside fixed noun phrases

A neuron in layer 13 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" in set phrases like "field of view", "cause of death" or "conflicts of interest", where the next word is fairly predictable. Turning it down made the model get stuck repeating "of the year of the year", so it seems to help keep phrases like this flowing.

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

    time during a comets apparition even⏎binoculars will be too powerful...⏎A telescope is a big mistake, it will have much too narrow a field of view.⏎Please, you should not just go out to an unfamiliar rural "dark

  2. #2 peak

    em examination, please contact the Social Worker at the State Coroner's Office.⏎In most coronial cases a post-mortem is required to determine the precise cause of death with certainty. However, on some occasions the Coroner can determine the cause

  3. #3 peak

    way, Gao and his colleagues demonstrated that the tool could reveal signs of pulmonary fibrosis in COVID long-haulers, thus helping to account for shortness of breath, coughing and other lung troubles. A diagnosis, he suggests, that

  4. #4 peak

    5i2.5⏎© 2018 Author. This work is licensed under the Creative Commons Attribution 4.0 International License.⏎Conflicts of Interest: None⏎Mild traumatic brain injury is defined as a traumatically

  5. #5 peak

    the world? 70% of all PET bottles are recycled here, compared to 31% in the USA. But before you give yourself a pat on the back for this achievement, can you name the invisible force behind it? It

  6. #6 peak

    actually delivering on the goal of limiting warming to 2°C. The authors drew on available data to establish global reserves at 1,294 billion barrels of oil, 192 trillion cubic metres of gas, 728

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: of my own of my of my of of of of of of of of of of of of of of of of of of of of of of of of of of of of of of of of of of of of of of of of of

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

    nests, but the Son of Man has no place to rest."⏎American Standard Version⏎And Jesus said unto him, The foxes have holes, and the birds of the heaven have nests; but the Son of man hath not where to lay his

  2. #2 peak

    atuation for someone, especially someone inappropriate or unattainable. … Unlike crushes and states of infatuation, love truly sees and accepts their object of affection. Love is an intense feeling of deep affection

  3. #3 peak

    about cartilage damage is a good place to start. There are times when cartilage damage is so significant that replacing the joint is necessary to help restore function and range of motion.⏎What Are the Primary Functions of Cartilage?⏎Cartilage plays a

  4. #4 peak

    Holman Christian Standard BibleJesus told him, “Foxes have dens, and birds of the sky have nests, but the Son of Man has no place to lay His

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. L11:1392 strongly excites 'of' in fixed technical phrases
  2. L11:2057 strongly excites
  3. L12:2176 excites 'of' after a place or role noun
  4. L8:1673 suppresses
  5. L12:2046 suppresses
  6. L11:2424 suppresses
  7. L11:1158 suppresses
  8. L12:1423 suppresses
  9. L12:1579 suppresses
  10. L11:2840 excites 'in' after a size measurement
  11. L8:1801 suppresses
  12. L8:202 excites
  13. L9:2196 excites
  14. L12:1116 suppresses 'of' in formal noun phrases, mixed
  15. L12:1053 suppresses
  16. L11:1274 suppresses
  17. L12:1126 excites
  18. L12:1984 suppresses
  19. L10:2377 excites
  20. L8:1541 excites
  21. L10:564 excites
  22. L11:173 suppresses
  23. L4:990 suppresses
  24. L12:1518 suppresses

Feeds later layers

  1. L17:1771 strongly suppresses
  2. L17:546 strongly suppresses
  3. L17:1241 suppresses
  4. L14:1737 suppresses
  5. L16:1855 suppresses
  6. L14:1037 suppresses
  7. L16:2715 suppresses
  8. L14:1259 suppresses
  9. L14:1393 suppresses
  10. L19:2095 suppresses
  11. L23:2504 suppresses
  12. L16:2743 suppresses
  13. L15:435 excites
  14. L16:302 suppresses
  15. L16:961 suppresses
  16. L14:539 suppresses
  17. L17:2463 suppresses
  18. L17:2736 suppresses
  19. L18:2467 suppresses
  20. L17:375 excites
  21. L20:2599 suppresses
  22. L16:434 suppresses
  23. L16:2443 suppresses
  24. L22:2882 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 -9.14 and -8.741 values between -7.15 and -6.751 values between -5.56 and -5.161 values between -4.36 and -3.971 values between -3.17 and -2.774 values between -2.77 and -2.379 values between -2.37 and -1.9824 values between -1.98 and -1.5835 values between -1.58 and -1.1844 values between -1.18 and -0.78137 values between -0.78 and -0.381300 values between -0.38 and 0.011906 values between 0.01 and 0.41397 values between 0.41 and 0.8125 values between 0.81 and 1.2112 values between 1.21 and 1.612 values between 1.61 and 2.015 values between 2.40 and 2.801 values between 2.80 and 3.201 values between 3.20 and 3.601 values between 6.38 and 6.78offnegativepositiveoften

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. 况
  2. ippers
  3. etypes
  4. ector
  5. ifiable
  6. quake
  7. emet
  8. 畿
  9. 平台上
  10. ifications

Suppresses

  1. -of
  2. _of
  3. Of
  4. Of
  5. _Of
  6. of
  7. _OF
  8. зрения
  9. interest
  10. concern