Neuron Explorer

Qwen3-0.6B

'of' after 'those' or 'many'

A neuron in layer 7 of Qwen3-0.6B. Its strongest snippets are fairly consistent: several of them peak on the same token. It is featured, so it has steering outputs.

What this neuron does

The neuron fires on a word like 'of' or 'that' that comes after a quantity word such as 'those', 'many' or 'some', and introduces a group that a part is taken from, like 'those of us' or 'many of the issues'. The steered text was unrelated, so the pattern comes only from 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

    to be no obvious health implications to excess contrast/saturation/sharpness as there are with salt, fat, and sugar.⏎But perhaps there are some subtle ones.⏎While there is a lot of concern about the effects sensory over-stimulation in

  2. #2 peak

    this tree are found in Palestine. It is a "very graceful tree, with long feathery branches and tufts closely clad with the minutest of leaves, and surmounted in spring with spikes of beautiful pink blosoms,

  3. #3 peak

    .⏎2625 In the first place these are prayers that the faithful hear and read in the Scriptures, but also that they make their own - especially those of the Psalms, in view of their fulfillment in Christ.96 The

  4. #4 peak

    , given enough time and sufficient access, they hope to catch a glimpse of the famous ship too. Only time will tell if that will actually happen, but those of us who are fans of Shackleton and his story are

  5. #5 peak

    First⏎thats right vegetarian spider⏎A tropical jumping spider that eats mostly plant buds has been identified, a new study says—making it the only known vegetarian out of some 40,000 spider species.⏎In the late

  6. #6 peak

    (secret service) as early as 3. 000 years ago. London was probably founded some seven years after the Roman invasion of Britain (those of you who know Asterix might

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 to be done with a single or a problem that can be solved with a simple logic. The problem is presented in the form of a problem that is often used in mathematics, and the solution is provided in the form of a single

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

    which states that our beliefs shape our actions. We do what we feel is right and this is what forms the organizational culture as a whole.⏎- The Simultaneity Principle – that states that appreciative inquiry or the way we question our internal

  2. #2 peak

    until the moment a piece is installed. He arrives at the gallery with barrels filled with the component pieces and lets the spirit of the day and the idiosyncrasies of the site

  3. #3 peak

    for years. And while some rumors are false --- sometimes intentionally --- many others are surprisingly accurate. The website www.snopes.com has surfaced as the rumor-skeptic's friend, collecting and verifying tales of every type.⏎DiFonzo is

  4. #4 peak

    bidities which contribute to progression of CHF, particularly if treatable is our current challenge and need to be pursued systematically and aggressively.⏎Among multiple co-morbidities, sleep-related disordered breathing (SRBD), is the most common and

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. L6:105 suppresses
  2. L5:800 excites
  3. L5:2220 suppresses
  4. L2:20 suppresses
  5. L4:2546 excites
  6. L6:1915 suppresses
  7. L1:67 excites
  8. L6:942 suppresses
  9. L6:84 excites
  10. L4:834 excites
  11. L3:58 excites
  12. L5:1273 excites
  13. L6:302 excites
  14. L2:803 excites
  15. L4:157 suppresses
  16. L6:2940 suppresses
  17. L4:509 suppresses
  18. L6:361 excites
  19. L4:420 suppresses
  20. L5:983 excites
  21. L0:1517 excites
  22. L3:2972 suppresses word endings in multi-token nouns
  23. L6:141 weakly suppresses
  24. L4:428 weakly excites

Feeds later layers

  1. L8:71 excites
  2. L10:930 excites
  3. L13:2099 excites
  4. L25:1890 suppresses
  5. L8:411 excites
  6. L11:870 weakly excites
  7. L12:571 weakly excites
  8. L9:152 weakly excites
  9. L15:1495 weakly excites
  10. L18:801 weakly suppresses
  11. L18:238 weakly excites
  12. L10:235 weakly excites
  13. L12:656 weakly excites
  14. L14:1601 weakly excites
  15. L17:1125 weakly excites
  16. L11:2733 weakly excites
  17. L9:787 weakly excites
  18. L8:965 weakly excites
  19. L18:737 weakly suppresses
  20. L14:2647 weakly excites 'and' or 'or' in split hyphen compounds
  21. L18:2929 weakly excites comma after a finished clause
  22. L17:553 weakly excites
  23. L16:525 weakly suppresses
  24. L19:1722 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 -1.72 and -1.601 values between -1.25 and -1.134 values between -1.13 and -1.014 values between -1.01 and -0.898 values between -0.89 and -0.788 values between -0.78 and -0.6624 values between -0.66 and -0.5446 values between -0.54 and -0.42116 values between -0.42 and -0.30307 values between -0.30 and -0.19669 values between -0.19 and -0.071851 values between -0.07 and 0.05525 values between 0.05 and 0.17169 values between 0.17 and 0.2978 values between 0.29 and 0.4135 values between 0.41 and 0.5219 values between 0.52 and 0.649 values between 0.64 and 0.769 values between 0.76 and 0.888 values between 0.88 and 1.004 values between 1.00 and 1.115 values between 1.11 and 1.233 values between 1.23 and 1.351 values between 1.35 and 1.472 values between 1.47 and 1.591 values between 1.71 and 1.821 values between 2.89 and 3.00offnegativepositiveoften

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. importe
  2. �单
  3. itives
  4. vard
  5. ?>'
  6. encer
  7. ipher
  8. �
  9. ;',
  10. import

Suppresses

  1. uada
  2. =log
  3. reproduced
  4. warranted
  5. =a
  6. Pale
  7. ма
  8. =i
  9. 鹃
  10. การทำ