Neuron Explorer

Qwen3-0.6B

prepositions after comparison words

A neuron in layer 14 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

This neuron fires on the small word that follows a comparison, such as 'to' in 'compare to', 'from' in 'indistinguishable from', or 'than' in 'less than'. Turning it up did not bring out this theme in the generated text, so the snippets are the clearest evidence.

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

    REC ITY OSC⏎ALL IAT SQU⏎See another brain teaser just like this one...⏎Or, just get a random brain teaser⏎If you become a

  2. #2 peak

    tour of this brave new theory at the frontier of physics, showing what some of these alternate realities might be like. Some universes may be almost indistinguishable from our own; others may contain variations of all of us, where we exist but

  3. #3 peak

    day, I am told to put my fingers firmly in my ears. Even then, when the four quarters are struck, the noise is phenomenal, but nothing compared to the striking of the hour bell, Big Ben. The belfry reverber

  4. #4 peak

    . The artistic atmosphere and community in America could not compare to the one in Europe. According to H.L.W. Dana, „Washington All

  5. #5 peak

    on Earth is not a claim for Chinese exceptionalism, indeed quite the opposite. Almost all the 20 essential ideas it identifies are the same or very similar to

  6. #6 peak

    , while at the same time can be accessed in a uniform manner by all languages that the .NET platform support. In other words, CLS is a subset of the full functionality of CTS.⏎- Common Language Run-time (CLR):⏎The

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 idea that the idea of the name "Carnegie" and the relationship between the two, the relationship between the two people, the name "Carnegie" and the 19th century, the relationship between the two,

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

    their different characteristics.⏎Two word system developed by Carolous Linnaeus to name species, first word identifies the genus of the organism, the second word is often a descriptive word that describes a characteristic of the organism.⏎Next large taxon in the

  2. #2 peak

    in the following sequence:⏎moral, friend, port, feet, race⏎AnswerBy adding the sound of the first five letters of the alphabet to the beginning of each word respectively, another word can be enunc

  3. #3 peak

    function is equal to a variable:⏎- Your function name can be designed using characters from alphanumeric and an underscore.⏎- Your function name does not have to start with a number⏎- Your function name has to be different from an existing function or language

  4. #4 peak

    the Union...⏎7th - 12th Social Studies & History⏎President Obama's State of the Union Address 2011⏎Students pretend they are journalists and have to write 10 questions to ask the President at

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. L11:2292 excites 'than' in comparisons
  2. L12:981 suppresses
  3. L6:984 suppresses
  4. L13:1944 suppresses
  5. L10:1465 suppresses
  6. L12:1945 excites
  7. L12:1197 suppresses
  8. L13:2434 weakly excites
  9. L12:1148 weakly suppresses
  10. L4:2034 weakly suppresses
  11. L13:1769 weakly excites
  12. L12:2692 weakly suppresses
  13. L12:2855 weakly excites
  14. L5:1317 weakly suppresses 'a' right after 'being'
  15. L10:1447 weakly suppresses
  16. L12:1496 weakly excites
  17. L5:872 weakly suppresses 'or' introducing an alternate name
  18. L11:1605 weakly suppresses
  19. L12:2298 weakly excites
  20. L6:1971 weakly suppresses
  21. L9:573 weakly excites
  22. L12:2930 weakly excites "and" joining contrasting pairs
  23. L9:1802 weakly suppresses
  24. L13:2356 weakly excites

Feeds later layers

  1. L16:963 suppresses
  2. L16:1181 excites
  3. L19:709 excites
  4. L16:2315 excites
  5. L16:2600 excites
  6. L16:1147 excites
  7. L16:935 suppresses
  8. L15:2006 excites
  9. L16:2521 excites
  10. L16:2039 weakly excites
  11. L18:2557 weakly excites
  12. L15:203 weakly excites
  13. L18:1039 weakly excites
  14. L16:101 weakly excites
  15. L19:2091 weakly excites
  16. L16:1045 weakly suppresses
  17. L18:1037 weakly suppresses
  18. L16:1959 weakly excites
  19. L16:2836 weakly excites
  20. L17:2631 weakly excites
  21. L15:1255 weakly excites
  22. L16:1913 weakly suppresses
  23. L20:1029 weakly excites
  24. L15:1145 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 -2.56 and -2.381 values between -1.33 and -1.151 values between -0.98 and -0.804 values between -0.80 and -0.6214 values between -0.62 and -0.4583 values between -0.45 and -0.27540 values between -0.27 and -0.102295 values between -0.10 and 0.08755 values between 0.08 and 0.26151 values between 0.26 and 0.4337 values between 0.43 and 0.6112 values between 0.61 and 0.785 values between 0.78 and 0.963 values between 0.96 and 1.132 values between 1.13 and 1.311 values between 1.31 and 1.491 values between 1.49 and 1.661 values between 2.01 and 2.191 values between 4.30 and 4.47offnegativepositiveoften

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. regar
  2. vous
  3. erreur
  4. ']")⏎
  5. ANNOT
  6. .Default
  7. 为了
  8. aptive
  9. ateur
  10. alled

Suppresses

  1. latlong
  2. 榧
  3. Piano
  4. gie
  5. 联
  6. 程
  7. 毀
  8. _relationship
  9. Tone
  10. мир