Neuron Explorer

Qwen3-0.6B

'of' in fixed technical phrases

A neuron in layer 11 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 fires on the word 'of' in set phrases from technical or medical writing, such as 'degrees of freedom', 'field of view', 'cause of death' and 'center of gravity'. Turning it up made the model repeat 'of' over and over, which fits the same theme.

Written by Claude from this neuron's activations and steering outputs. Confidence: high. 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

    movements in three-dimensional (3D) space is a complicated task, a challenge to both biological and artificial systems. Increasing the number of degrees of freedom of the arm makes this task more complicated (Hollerbach,

  2. #2 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

  3. #3 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

  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 doctor will bend your injured knee and check for clicks, snaps and "catches" within the joint. Your doctor also will evaluate your knee's range of motion and will maneuver your knee to see whether your meniscus is sensitive to

  6. #6 peak

    trim-The angle with the horizontal surface of the water assumed by the float or hull under given conditions. trimming moment-The moment about a reference point, usually the center of gravity, exerted by the seaplane hull or float when held at a

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 a dog is a red Apple watch 1000 dollars 20000 yen 30000円 10000円 10000円 100

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

    is about the formative years of the fallen king. Out of print, but sometimes available from Alibris.⏎The Countess and the King: A Novel of the Countess of Dorchester and King James II by Susan Holloway Scott.

  2. #2 peak

    lest you forget the things your eyes have seen and lest they stray from your heart all the days of your life. And you are to make them known to your children and to your children’s children – the day you stood before the L-ord

  3. #3 peak

    I will make your seed to multiply as the stars of heaven, and I will give to your seed all these countries. And in your seed shall all the nations of the earth be blessed because Abraham obeyed my voice, and kept my charge,

  4. #4 peak

    oil. But if you don’t want to read through the study, just watch this video from the Renewable Fuels Association. They say a picture is worth a thousand words and in this case I think they’re right.<|endoftext|>Traf-O-

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. L8:2385 suppresses
  2. L8:202 excites
  3. L8:1673 suppresses
  4. L5:2462 weakly excites
  5. L4:1369 weakly excites
  6. L6:2723 weakly excites "way of" before life, looking, eating
  7. L6:13 weakly excites
  8. L9:2985 weakly excites
  9. L6:2950 weakly suppresses
  10. L8:7 weakly excites
  11. L5:2269 weakly excites
  12. L0:1556 weakly excites
  13. L4:1347 weakly suppresses
  14. L5:2988 weakly suppresses
  15. L7:888 weakly suppresses
  16. L8:6 weakly suppresses
  17. L6:181 weakly excites periods in abbreviations and the 's in names
  18. L7:1970 weakly suppresses
  19. L2:2964 weakly suppresses
  20. L6:1995 weakly suppresses comma after a 'that' or 'who' clause
  21. L6:1745 weakly excites
  22. L9:335 weakly excites 'of' after nouns like anniversary or onset
  23. L4:1614 weakly suppresses
  24. L2:1534 weakly excites

Feeds later layers

  1. L13:1335 strongly excites 'of' inside fixed noun phrases
  2. L17:1771 strongly excites
  3. L14:1737 excites
  4. L17:546 excites
  5. L16:2715 excites
  6. L12:576 excites 'of' in fixed phrases like table of contents
  7. L23:2504 excites
  8. L26:711 excites 'years' after an age number
  9. L15:646 excites
  10. L22:142 suppresses 'of' after a quantity or noun phrase
  11. L13:1659 excites
  12. L20:2599 excites
  13. L14:1259 excites
  14. L18:2467 excites
  15. L16:1855 excites
  16. L12:2176 excites 'of' after a place or role noun
  17. L16:961 excites
  18. L23:567 excites
  19. L19:2622 excites
  20. L14:1265 excites
  21. L17:1241 excites
  22. L12:887 excites
  23. L13:700 excites
  24. L17:870 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 -0.90 and -0.751 values between -0.75 and -0.6118 values between -0.61 and -0.4787 values between -0.47 and -0.33444 values between -0.33 and -0.191157 values between -0.19 and -0.051530 values between -0.05 and 0.09536 values between 0.09 and 0.2392 values between 0.23 and 0.3715 values between 0.37 and 0.516 values between 0.51 and 0.654 values between 0.65 and 0.794 values between 0.79 and 0.931 values between 0.93 and 1.073 values between 1.35 and 1.492 values between 1.49 and 1.642 values between 1.64 and 1.781 values between 1.78 and 1.921 values between 3.60 and 3.741 values between 3.74 and 3.882 values between 4.59 and 4.73offnegativepositiveoften

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. -of
  2. of
  3. Of
  4. Of
  5. _of
  6. _Of
  7. _OF
  8. →of
  9. OfWork
  10. OF

Suppresses

  1. icolor
  2. 这些问题
  3. öne
  4. 年底
  5. elow
  6. enes
  7. št
  8. #ifdef
  9. licht
  10. egade