Neuron Explorer

Qwen3-0.6B

"only" in "it is only" constructions

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

This neuron fires on the word "only", especially in phrases like "it is only due to" or "but only if", where the writer limits or qualifies a claim. Turning it up did not give a clear theme in the model's replies, so its effect on writing is unclear.

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

    deep cleaning and/or scaling and root planing for more severe cases<|endoftext|>Considering the fact that half of you reading this right now are probably wearing one, It’s only right to start this week off with the most commonplace of all acronymic items–

  2. #2 peak

    cars are coming - if you can fill up⏎LONDON (Reuters) - Britain's hydrogen fuel cell car fleet may hit top gear within five years, but only if there is enough investment in filling stations, the UK Hydrogen and Fuel Cells

  3. #3 peak

    finance and law. As the world changes, most of our financial matters have moved seamlessly online. Our digital identity is lagging in terms of adoption but it is only due to the sensitivity of the matter at hand.⏎Digital identity is used in relation

  4. #4 peak

    kill very quickly. And it is not the only danger that we may face at home and in public places. A few basic precautions can save your life — but only if you follow them!⏎Fire safety at home⏎Your biggest lifes

  5. #5 peak

    instinctive manner: it is to know the reasons behind these rules and, not less importantly, to know their limitations.⏎Regrettably, it seems it is only in times of trouble and uncertainty when we begin to realize tradition is a living and

  6. #6 peak

    looking ahead to a problem on the horizon: Many Covid-19 survivors will have long-term lung injuries, and medicine has little to offer them.⏎There’s only scant data on how many patients who recover from Covid-19 are left with

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, for all the time, but have been, for all the time, but have, for all the same time, I have been, in the same time, the same time, but I have been, in all the

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

    01).⏎Predator conservation has to date operated primarily within the boundaries of existing protected areas, but there are several limitations in relying solely upon this approach: only around 5% of the world’s land area is formally protected (Gittleman

  2. #2 peak

    differences they noticed and then embed this in the class website".<|endoftext|>Instructions: In this discussion, you will need to post your response (no fewer than 200 words and including citation and research) before you can see a

  3. #3 peak

    an activity that has many benefits for the body⏎Yoga is more than just physical activity. In the Indian tradition, it is a real way of life comprising

  4. #4 peak

    /stereo/article/view/6807<|endoftext|>The term “education technology” (or “edtech,” as it’s commonly known) refers to more than just learning via computer. Edtech has existed in various forms for as long as education

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. L4:661 strongly excites
  2. L10:652 suppresses
  3. L9:2343 suppresses
  4. L4:2502 suppresses
  5. L2:2153 suppresses
  6. L4:3039 excites
  7. L8:140 excites
  8. L15:2689 excites the word 'only' mid-sentence
  9. L11:1697 weakly excites
  10. L14:1400 weakly suppresses
  11. L15:1139 weakly suppresses
  12. L15:2637 weakly suppresses
  13. L13:948 weakly suppresses
  14. L11:678 weakly suppresses
  15. L14:536 weakly suppresses
  16. L7:63 weakly excites
  17. L15:469 weakly excites
  18. L1:2119 weakly excites
  19. L7:2753 weakly excites
  20. L16:1422 weakly suppresses
  21. L3:2933 weakly suppresses
  22. L11:2367 weakly suppresses
  23. L4:1830 weakly excites
  24. L13:2845 weakly excites

Feeds later layers

  1. L23:2337 excites
  2. L18:1130 excites
  3. L19:2011 excites
  4. L21:2533 excites
  5. L18:2478 excites
  6. L18:2883 excites
  7. L21:1226 suppresses
  8. L20:1279 excites
  9. L18:590 excites
  10. L18:2755 weakly suppresses
  11. L20:2305 weakly excites
  12. L19:1298 weakly excites
  13. L18:2181 weakly suppresses
  14. L26:271 weakly suppresses
  15. L21:1349 weakly excites
  16. L20:2339 weakly excites
  17. L23:2083 weakly excites 'a' meaning one single
  18. L20:2494 weakly suppresses
  19. L23:1498 weakly excites
  20. L27:2346 weakly excites
  21. L23:2170 weakly excites
  22. L18:2206 weakly suppresses
  23. L25:549 weakly suppresses
  24. L24:242 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.

706 values between -2.10 and -0.793176 values between -0.79 and 0.5210 values between 0.52 and 1.848 values between 1.84 and 3.151 values between 3.15 and 4.461 values between 5.78 and 7.091 values between 8.41 and 9.721 values between 14.97 and 16.291 values between 17.60 and 18.911 values between 20.23 and 21.541 values between 22.85 and 24.171 values between 49.12 and 50.44offnegativepositiveoften

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. izioni
  2. ertiary
  3. iciones
  4. 一件事
  5. 砜
  6. sofar
  7. "..
  8. ões
  9. motivate
  10. oser

Suppresses

  1. all
  2. 歹
  3. -cr
  4. ibernate
  5. 所有的
  6. AY
  7. 年代
  8. 任意
  9. ursal
  10. ay