Neuron Explorer

Qwen3-0.6B

the word matter in no matter phrases

A neuron in layer 17 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

It fires on the word "matter" in phrases like "no matter how", "no matter what" and "no matter where". It is very consistent across the examples. Turning it up made the model produce more "or" and "whether or not" style phrasing, which is a related idea of alternatives, though the outputs are otherwise mixed.

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

    Sekonyer village, central Borneo, remained poor no matter how much they burned surrounding forest to expand their farmland.⏎“Tragically, no matter how many resources are exploited

  2. #2 peak

    more kinds of plants in your yard, you will attract more animals, and help to increase your neighbourhood’s biodiversity.<|endoftext|>Want to beat your Scrabble friends no matter where you are?WordSolver Android App!⏎3 Definitions of Rifts⏎The

  3. #3 peak

    want whenever you want without having to work for it. It is about being convinced that you deserve things you want and someone has got to give them to you no matter what.⏎Below are what I believe are some of the pitfalls of this entitlement mentality

  4. #4 peak

    flare of a torch. They would scoop the substance from the spring by sopping it up with blankets and wringing the liquid out by hand into pots. No matter how many times they repeated that process, the spring would replenish itself with more

  5. #5 peak

    best—which can be very true—but I have found that it’s the simple things in life that teach our children the most.⏎Since he could barely walk, no matter where we were outside, my son Kendall was immediately drawn to sticks of every different

  6. #6 peak

    there may be better vision models in nature than the human eye movement. The insect or bird worlds probably have superior versions of eye movement than human eye movement.⏎No matter which animal or human example you use, the Creator got it right the first time

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 been, at least,, at least,, at least, but not sure, most, but, likely, maybe, at least, but, at least, maybe, at least, and, to at least, most,

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

    . Excitingly, these histones, when expressed in E. coli, bind the genome nearly<|endoftext|>Definition of Nupe in English:⏎noun (plural same or Nupes)⏎2 [mass noun] The Benue-Congo language of

  2. #2 peak

    cool and moist. This is especially beneficial during the hottest, dryest months. During drought-like conditions, moisture can evaporate. Mulch will help to prevent or lessen this effect.⏎Weeds grow at a much faster rate than your garden’s

  3. #3 peak

    data table above.⏎Have you ever built an app based on Excel?⏎Method 1: The easiest way (VLOOKUP & MATCH)⏎Probably the easiest – or at least the shortest – way of returning values in 2 search dimensions is the

  4. #4 peak

    University of Chicago, the University of California, Davis, and the University of California, Berkeley.⏎As the Biden administration pledges to move the nation toward electric vehicles, or EVs, and states like California work to ban the sale of new completely gas

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. L14:3046 excites
  2. L15:2935 suppresses
  3. L4:108 excites "or" offering a choice in web text
  4. L15:3059 suppresses 'and' or 'or' joining the last list items
  5. L4:556 excites
  6. L5:1203 suppresses
  7. L0:1177 suppresses
  8. L12:422 weakly suppresses
  9. L10:712 weakly suppresses
  10. L1:1187 weakly excites
  11. L14:3025 weakly suppresses
  12. L16:2436 weakly suppresses
  13. L16:71 weakly excites
  14. L15:633 weakly suppresses
  15. L13:2339 weakly excites
  16. L7:1917 weakly suppresses
  17. L13:104 weakly suppresses
  18. L8:2002 weakly suppresses
  19. L16:157 weakly excites
  20. L4:653 weakly excites "that" after "such" or "such a way"
  21. L8:2189 weakly excites
  22. L1:491 weakly excites
  23. L15:2508 weakly excites
  24. L11:91 weakly excites

Feeds later layers

  1. L19:2293 excites
  2. L19:289 suppresses
  3. L18:2517 excites
  4. L20:1334 excites
  5. L25:1270 excites
  6. L18:2362 excites
  7. L23:223 excites
  8. L18:2197 excites
  9. L18:1138 excites
  10. L27:376 excites
  11. L25:41 suppresses
  12. L18:2896 excites
  13. L20:1670 weakly excites
  14. L25:576 weakly excites
  15. L20:1599 weakly excites
  16. L21:728 weakly excites
  17. L19:1352 weakly excites
  18. L26:492 weakly excites
  19. L22:2765 weakly excites
  20. L18:3036 weakly excites
  21. L19:2700 weakly excites
  22. L22:1414 weakly excites
  23. L27:656 weakly excites
  24. L24:1071 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.

3 values between -1.71 and -1.16178 values between -1.16 and -0.612277 values between -0.61 and -0.061391 values between -0.06 and 0.4919 values between 0.49 and 1.046 values between 1.04 and 1.585 values between 1.58 and 2.137 values between 2.13 and 2.684 values between 2.68 and 3.232 values between 3.23 and 3.784 values between 4.33 and 4.881 values between 4.88 and 5.421 values between 5.42 and 5.972 values between 5.97 and 6.522 values between 6.52 and 7.071 values between 7.07 and 7.622 values between 7.62 and 8.171 values between 10.36 and 10.911 values between 10.91 and 11.461 values between 19.69 and 20.23offnegativepositiveoften

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. 或是
  2. 或多
  3. or
  4. 多么
  5. |h
  6. 有多么
  7. 何种
  8. whether
  9. 或者其他
  10. |i

Suppresses

  1. 且
  2. 只有
  3. 只能
  4. ailand
  5. 也只有
  6. 除了
  7. 两个
  8. ştir
  9. 尽量
  10. 不能再