Neuron Explorer

Qwen3-0.6B

"for" after "hard" or "difficult"

A neuron in layer 2 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 "for" in phrases like "hard for", "difficult for" or "easier for", right before the person affected is named. Turning it up did not produce an obvious change in the text.

Written by Claude from this neuron's activations and steering outputs. Confidence: high. 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

    radiation, and other agents, are published in a Special Report in the August issue of The Lancet Oncology.⏎Source: Medical News Today<|endoftext|>It’s hard for even the most rigorous of scientists to argue with an elegant experimental design and a pretty

  2. #2 peak

    the impact of completely remaking the lives of many working people after the war. The US entered a time of great prosperity after the war, making it much easier for working people to make a good living. In this sense, the war was a

  3. #3 peak

    . This makes it difficult for businesses to forecast the cost of fuel and can cast doubts over the future of their

  4. #4 peak

    the soil is fit for planting, probably past the best time for sowing.⏎The loss of draft animals will make it hard for farmers to<|endoftext|>Calò is a prime example of the merging of language and culture

  5. #5 peak

    the depreciating mentality of Columbus and his hopes. As each voyage is unsuccessful in producing Oriental splendors or in establishing relations with the Great Kahn, it becomes harder for Columbus to persuade others to support his missions

  6. #6 peak

    fear of missing out'⏎CHARLESTON, W.Va. -- As the constant need for communication is becoming the social norm, it's increasingly difficult for people

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 working on it. I have been writing it. I have been thinking about it. I have been writing it again. I have been thinking about it again. I have been writing it again. I have been thinking about it

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 gasoline-powered fleet.⏎That’s according to the new data published from the University of Chicago, the University of California, Davis, and the University of

  2. #2 peak

    agent(s) by a route other than IV; (PO, PR, Intranasal, IM) and appropriate monitoring.⏎Regional Anesthesia: A term used for local anesthesia.⏎Removal of the tip of a tooth root.<|endoftext|>The Adams

  3. #3 peak

    mice into eight separate lines – four lines bred for high levels of daily running, with the remaining four used as controls – and measured

  4. #4 peak

    –5, 6–8, 9–12⏎Important events during the presidency of Jimmy Carter.⏎President Jimmy Carter agreed to answer seven questions selected from several hundred posted by Scholastic students.⏎A time line showing the events in

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. L1:1963 weakly excites
  2. L1:2500 weakly excites
  3. L0:1244 weakly suppresses
  4. L1:1804 weakly suppresses
  5. L0:1543 weakly excites
  6. L0:1778 weakly suppresses
  7. L1:1230 weakly excites
  8. L1:2330 weakly suppresses
  9. L0:1447 weakly excites
  10. L0:2989 weakly suppresses
  11. L1:1892 weakly excites
  12. L0:2922 weakly suppresses
  13. L0:2765 weakly excites
  14. L1:2720 weakly suppresses
  15. L0:2301 weakly excites
  16. L0:931 weakly excites
  17. L0:897 weakly suppresses
  18. L0:84 weakly suppresses
  19. L0:1369 weakly suppresses
  20. L0:376 weakly excites
  21. L0:3 weakly suppresses
  22. L1:1960 weakly excites
  23. L1:92 weakly excites
  24. L0:1852 weakly suppresses

Feeds later layers

  1. L12:2535 excites
  2. L7:304 excites
  3. L23:1062 excites
  4. L8:2680 weakly excites
  5. L25:343 weakly excites
  6. L14:2150 weakly excites
  7. L5:2365 weakly suppresses
  8. L20:2180 weakly excites
  9. L20:2161 weakly excites
  10. L10:2426 weakly excites
  11. L20:2229 weakly excites
  12. L25:1639 weakly excites
  13. L15:2843 weakly excites
  14. L9:654 weakly excites
  15. L23:2933 weakly excites
  16. L22:94 weakly suppresses
  17. L18:2120 weakly excites
  18. L14:1169 weakly excites
  19. L13:1162 weakly excites
  20. L23:436 weakly excites
  21. L25:1742 weakly excites
  22. L6:1547 weakly suppresses
  23. L11:2227 weakly suppresses
  24. L20:954 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.

2 values between -1.67 and -1.421 values between -1.18 and -0.935 values between -0.93 and -0.698 values between -0.69 and -0.44119 values between -0.44 and -0.202794 values between -0.20 and 0.05906 values between 0.05 and 0.2940 values between 0.29 and 0.5411 values between 0.54 and 0.793 values between 0.79 and 1.034 values between 1.03 and 1.285 values between 1.28 and 1.523 values between 1.52 and 1.772 values between 1.77 and 2.011 values between 2.01 and 2.261 values between 2.26 and 2.501 values between 2.50 and 2.751 values between 3.24 and 3.491 values between 7.90 and 8.15offnegativepositiveoften

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. ocht
  2. rometer
  3. rieb
  4. translator
  5. orque
  6. correspondent
  7. :x
  8. endant
  9. orary
  10. criança

Suppresses

  1. led
  2. Citation
  3. 免责声明
  4. amation
  5. tà
  6. ."""⏎⏎
  7. .gdx
  8. ['$
  9. glGen
  10. Sundays