Neuron Explorer

Qwen3-0.6B

'so' before much or many

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 responds to the word 'so' when it means 'so much', 'so many' or 'so quickly', as in 'missed by so many news sources'. It is switched off, and even pushed the other way, when 'so' is followed by an adjective like 'so vast' or 'so covert'. Turning it up did not give a clear shared theme.

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

    several common cosmetic products, the harmful ingredient, the purpose for incorporating the chemical, and the adverse effect. So why is this still going on today when we know so much more about the effects? Unfortunately cosmetics are a low priority because of they are

  2. #2 peak

    a tautology: US policy is democratic because America is free. One suspects that if there was more truth to the assertion it would not have to be repeated so frequently, but merely be understood.⏎But, let

  3. #3 peak

    CPU hours and producing a hundred terabytes of data. And yet, when you ponder the vast sweep of space and time being modeled, it seems a marvel that so much universe can be squeezed into such a small box<|endoftext|>Tupac Shakur

  4. #4 peak

    with more alert minds they should be more receptive to instruction.⏎The benefits are so obvious, in fact, it’s hard to understand how so many school officials were so easily motivated to do away with physical education classes in the first place.⏎After seeing

  5. #5 peak

    contrast, an `io soaring over the Panaewa farm lots bears no resemblance to another hawk. It must have arrived a long time ago to have changed so much. But how long ago was that?⏎The answers have come recently by a

  6. #6 peak

    . An expert at the Coastal Bend Bays and Estuaries Program (CBBEP) said things could have been much worse had the state agencies not responded so quickly.⏎Just north of North Beach, along Highway 181, is

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: what is the value of the score of the current score in the game that I have built up to a point that it's almost 30% that I can't make up the time that I have made it up to now that I

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

    it sank with its vast cargo of precious stones, jewellery, gold, silver and tobacco still on board. In fact, the value of this ravaged fleet was so vast that the Spaniards spent a decade attempting to salvage the remains. They brought

  2. #2 peak

    - The Something is very different from the hunters and their dogs (the speaker knows all about them). The Something is far more covert. In fact, it’s so covert that no one sees or hears it make gaps in the wall.⏎- The

  3. #3 peak

    he leads his black soldiers to death,⏎he cannot bend his back.⏎- By the time the 54th infantry fights its last battle, the Colonel is so exhausted from fighting that he

  4. #4 peak

    one-quarter of the global average, and nearly 700 million of its citizens live in regions considered highly water-stressed. Meanwhile, groundwater depletion has been so significant in the areas around Beijing that parts of the city are falling into the earth

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. L5:1364 excites
  2. L10:2106 suppresses
  3. L7:2914 suppresses
  4. L8:14 excites
  5. L5:2308 suppresses
  6. L4:656 excites
  7. L9:2328 suppresses
  8. L8:7 weakly excites
  9. L4:2688 weakly suppresses
  10. L7:1990 weakly suppresses
  11. L3:1953 weakly excites 'such' after 'no' or 'any'
  12. L1:2005 weakly suppresses
  13. L10:2935 weakly excites
  14. L7:2331 weakly suppresses
  15. L7:191 weakly excites
  16. L10:487 weakly excites
  17. L7:2216 weakly excites
  18. L7:460 weakly suppresses
  19. L2:2335 weakly suppresses
  20. L9:1423 weakly excites
  21. L8:1161 weakly suppresses
  22. L3:937 weakly suppresses
  23. L10:1477 weakly excites
  24. L4:3051 weakly excites

Feeds later layers

  1. L16:2782 strongly suppresses
  2. L17:2863 suppresses
  3. L15:2168 suppresses
  4. L16:1838 suppresses
  5. L14:1127 suppresses
  6. L20:1312 suppresses
  7. L14:2082 suppresses
  8. L16:2066 suppresses
  9. L15:906 suppresses
  10. L16:1802 suppresses
  11. L14:2132 excites
  12. L18:593 excites
  13. L13:958 suppresses
  14. L16:1645 suppresses
  15. L12:1668 weakly suppresses
  16. L12:631 weakly suppresses
  17. L13:706 weakly suppresses
  18. L17:626 weakly suppresses
  19. L13:2509 weakly suppresses
  20. L14:1960 weakly suppresses
  21. L21:881 weakly suppresses comma after 'if' clause in prose, braces in code
  22. L16:881 weakly suppresses
  23. L13:883 weakly suppresses
  24. L16:2975 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 -10.19 and -9.881 values between -9.88 and -9.571 values between -6.45 and -6.141 values between -3.03 and -2.711 values between -2.09 and -1.783 values between -1.47 and -1.162 values between -0.85 and -0.5342 values between -0.53 and -0.221763 values between -0.22 and 0.091797 values between 0.09 and 0.40272 values between 0.40 and 0.7123 values between 0.71 and 1.021 values between 1.96 and 2.27offnegativepositiveoften

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. Tech
  2. ."),⏎
  3. 但这
  4. Tech
  5. ").⏎⏎
  6. Aid
  7. 但也
  8. 最大的
  9. ."));⏎
  10. .'),⏎

Suppresses

  1. {}{⏎
  2. ترا
  3. getParent
  4. inosaur
  5. _METADATA
  6. ={()=>
  7. iena
  8. .getProject
  9. <article
  10. ampa