Neuron Explorer

Qwen3-0.6B

'of' after 'property' or 'feature'

A neuron in layer 1 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' when it comes right after nouns like 'property', 'feature' or 'characteristic', as in 'a property of the system'. Turning it up did not produce a clear change in behaviour that matches this idea.

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 compiler takes care of that.⏎> Another example is to imagine a Tree in which the leaves contain⏎> "objects." If I want to change a property of one of those leaf objects,⏎You can't in general, the thing with a

  2. #2 peak

    expressions⏎Integer Practice Problems - Addition⏎Review and Practice Problems for adding positive and negative numbers⏎<|endoftext|>In physics, a conservation law states that a particular measurable property of an isolated physical system does not change as the system evolves over time. Exact conservation

  3. #3 peak

    System (CTS):⏎Each programming language designer has to specify a very important property of it, which is called type system. The type system indicates which data type are

  4. #4 peak

    on their own behalf and through their own stores. The dealer can independently set the final price of the goods or use the manufacturer’s recommended price.⏎An important feature of the dealer is that he takes the last place in the commodity exchange

  5. #5 peak

    of a pyruvate kinase splice-variant shows therapeutic promise⏎Cold Spring Harbor, N.Y.⏎– Cancer cells grow fast. That’s an essential characteristic of what makes them cancer cells. They’ve crashed through all the cell-cycle checkpoints and

  6. #6 peak

    cells, or cells sensitive to different wavelength ranges, the organism would theoretically be able to perceive colour or at the very least colour differences. Polarisation, another property of EM radiation, can be detected by some organisms, with insects and cephalop

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: the state of a country that is a country. So, the country is a country. So, the country is a country. So, the country is a country. So, the country is a country. So, the country is a

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

    the Legion of the Seventh Seal and the First Shogun. As to whether it was a foreign invasion or a civil war it is not known outside of Hachiman, for Hachiman has been isolated for many years, the only contact

  2. #2 peak

    azzucato. Copyright © 2018. Available from PublicAffairs, an imprint of Perseus Books, LLC, a subsidiary of Hachette Book Group, Inc.⏎The January 2010 edition of The

  3. #3 peak

    to the south-west Khulian name for the God of Battle Rage, Oiden. Perhaps some ancient link can be inferred.⏎The Shogunate of Hachiman is just over five hundred years old. A huge battle took place around

  4. #4 peak

    ogun is not known for sure. The first Shogun was still a good 800 years after the Splitting of Irritaria and Hachiman was probably ruled by an Emperor/ress before the Shoguns took complete

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. L0:546 weakly suppresses
  2. L0:886 weakly suppresses
  3. L0:1228 weakly excites
  4. L0:979 weakly excites
  5. L0:2820 weakly excites
  6. L0:178 weakly suppresses
  7. L0:2606 weakly excites
  8. L0:2621 weakly suppresses
  9. L0:2113 weakly excites
  10. L0:2781 weakly excites
  11. L0:1370 weakly excites
  12. L0:1301 weakly suppresses
  13. L0:1224 weakly suppresses
  14. L0:1745 weakly suppresses quantity word after large, high or low
  15. L0:84 weakly suppresses
  16. L0:283 weakly excites
  17. L0:2975 weakly excites
  18. L0:1877 weakly excites
  19. L0:614 weakly suppresses
  20. L0:2333 weakly suppresses
  21. L0:1543 weakly suppresses
  22. L0:2456 weakly excites
  23. L0:1630 weakly suppresses
  24. L0:2207 weakly suppresses

Feeds later layers

  1. L10:1385 weakly suppresses
  2. L7:845 weakly suppresses
  3. L6:1201 weakly excites
  4. L14:962 weakly suppresses
  5. L14:980 weakly excites
  6. L7:543 weakly excites
  7. L2:1732 weakly suppresses
  8. L25:1380 weakly suppresses
  9. L2:674 weakly suppresses
  10. L24:991 weakly suppresses
  11. L6:3032 weakly suppresses
  12. L15:1879 weakly excites
  13. L2:813 weakly excites
  14. L13:2873 weakly suppresses
  15. L11:1320 weakly suppresses
  16. L21:1579 weakly excites
  17. L9:1198 weakly suppresses
  18. L2:1755 weakly excites
  19. L9:1228 weakly excites
  20. L9:956 weakly excites
  21. L17:946 weakly suppresses
  22. L10:902 weakly excites
  23. L13:2099 weakly suppresses
  24. L13:1097 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 -1.42 and -1.342 values between -0.85 and -0.772 values between -0.77 and -0.681 values between -0.68 and -0.603 values between -0.60 and -0.526 values between -0.52 and -0.4411 values between -0.44 and -0.3636 values between -0.36 and -0.2786 values between -0.27 and -0.19267 values between -0.19 and -0.11765 values between -0.11 and -0.031601 values between -0.03 and 0.06768 values between 0.06 and 0.14262 values between 0.14 and 0.2254 values between 0.22 and 0.3018 values between 0.30 and 0.386 values between 0.38 and 0.474 values between 0.47 and 0.554 values between 0.55 and 0.632 values between 0.63 and 0.711 values between 0.71 and 0.792 values between 0.79 and 0.882 values between 0.88 and 0.961 values between 0.96 and 1.041 values between 1.29 and 1.372 values between 1.78 and 1.86offnegativepositiveoften

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. emain
  2. 勋
  3. ess
  4. едь
  5. applications
  6. предус
  7. \data
  8. verständ
  9. ronic
  10. McDon

Suppresses

  1. lake
  2. +-+-+-+-+-+-+-+-
  3. овал
  4. owski
  5. sposób
  6. opi
  7. 办法
  8. 之心
  9. hma
  10. ubit