Neuron Explorer

Qwen3-0.6B

the word 'fiber' or 'fibre'

A neuron in layer 3 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on the word 'fiber' (or 'fibre'), in food and health writing as well as in talk about materials. Turning it up did not make the model's replies focus on fiber, though, so the link is only visible in the text it reads.

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

    B6 and E. Mineral content includes magnesium, manganese, zinc, calcium, copper, phosphorous and iron. These nutrients bring you various health benefits.⏎Fiber-rich foods promote overall good health. They also enable healthy weight loss. The fiber

  2. #2 peak

    structure used to scrape and cut food, such as algae, off rocky surfaces. The teeth are built of protein frames reinforced by closely packed nanofibers of a mineral called goethite.⏎When scientists attempted to pull this light

  3. #3 peak

    Fibre Crops Legislative Bill into law.⏎Scientist at Uganda's National Agricultural Research Organization

  4. #4 peak

    can be processed into rubber, guayule also reportedly produces resin that can be used in adhesives, flavors, fragrances, and biofuel.⏎Fibrous material from the plant can

  5. #5 peak

    "For the next five or ten years, this is the challenge," Barber says of efforts to bring such natural designs into engineering. (See "Twisting Everyday Fibers Could Make 'Smart Clothes' a Reality.")⏎Performance engineers drawing inspiration from a lim

  6. #6 peak

    to the new flavours.⏎As we age our digestion can become less efficient, so it’s important to include more fibre in your diet. An easy way to incorporate fibre into your everyday routine, is to start your morning with a high fibre cereal.

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 paid $X$-A-10000000000000000000000000000000000000

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

    but contradictory results have been reached. The only excuse for the present paper is to draw attention more closely to the relation between the pomerium2 of the Palatine city and Roma quadrata.⏎So far as I know, the only definite

  2. #2 peak

    2,500 to take down. My guess was that you can kill a tree by later covering up the trunk flare.⏎— Bob Tingler, Palatine⏎In answer to your first question, it is generally best not to amend

  3. #3 peak

    It was built by the famous Boston architect Charles Bulfinch⏎Charles Bulfinch was an early American architect, and has been regarded by many as the first

  4. #4 peak

    and bravery," during which he had distinguished himself by breaking through the Spanish line which separated Pinar del Río Province from Havana Province. He fought alongside General Calixto García, and alongside Máximo Gómez with his ragged band of

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. L2:2715 weakly suppresses
  2. L1:951 weakly excites
  3. L2:1494 weakly suppresses
  4. L1:1674 weakly excites
  5. L1:2266 weakly suppresses
  6. L1:572 weakly excites
  7. L2:2328 weakly suppresses
  8. L1:2922 weakly excites
  9. L2:237 weakly excites
  10. L1:333 weakly suppresses
  11. L2:398 weakly suppresses
  12. L0:1224 weakly suppresses
  13. L1:338 weakly suppresses
  14. L0:58 weakly excites
  15. L1:2677 weakly suppresses
  16. L2:126 weakly excites
  17. L1:1357 weakly excites
  18. L2:1199 weakly suppresses
  19. L0:178 weakly suppresses
  20. L2:1374 weakly suppresses
  21. L2:1906 weakly suppresses
  22. L0:947 weakly suppresses
  23. L0:1301 weakly suppresses
  24. L1:331 weakly suppresses

Feeds later layers

  1. L6:2170 weakly suppresses
  2. L9:1347 weakly suppresses
  3. L14:1701 weakly excites
  4. L18:1076 weakly suppresses
  5. L8:2764 weakly suppresses
  6. L4:2772 weakly suppresses
  7. L4:2874 weakly suppresses
  8. L7:778 weakly suppresses
  9. L5:1365 weakly suppresses
  10. L9:2489 weakly suppresses
  11. L10:2806 weakly excites
  12. L15:2403 weakly suppresses
  13. L12:2533 weakly suppresses
  14. L23:1703 weakly excites
  15. L9:3044 weakly suppresses
  16. L25:1475 weakly excites
  17. L23:2726 weakly excites
  18. L24:2370 weakly excites
  19. L11:2939 weakly suppresses
  20. L5:469 weakly suppresses line breaks inside sentences
  21. L11:2866 weakly excites
  22. L5:256 weakly suppresses
  23. L14:483 weakly excites
  24. L7:1131 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.

41 values between -0.52 and -0.242797 values between -0.24 and 0.041057 values between 0.04 and 0.3212 values between 0.32 and 0.591 values between 10.32 and 10.60offnegativepositiveoften

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. BSP
  2. duto
  3. 本报
  4. 日消息
  5. .bp
  6. URLConnection
  7. abyrinth
  8. _bp
  9. floatValue
  10. ’y

Suppresses

  1. 客
  2. 符
  3. around
  4. {"
  5. 叫
  6. ater
  7. oun
  8. ienne
  9. olecule
  10. ObjectName