Neuron Explorer

Qwen3-0.6B

comma after 'in this article'

A neuron in layer 16 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

The neuron fires on the comma that follows a phrase like 'In this article' or 'In this essay', where the writer is announcing what the text will cover. When it was turned up, the model's replies drifted into rambling, unrelated topics, so the steering results don't add much.

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

    know, there are no modules that can identify offshore areas that do not touch other neighbor areas in the same layer.⏎In this article, I’ll just discuss spatial dissolving to keep it simple and focused. Figure

  2. #2 peak

    number of academic journals is because it helps them choose a journal to submit their articles.⏎In this article, I will try to answer and discuss this question as comprehensively as possible. We

  3. #3 peak

    effort and time, while smart work is about finding the most effective and efficient way to get things done. In this essay, we will discuss the differences between hard work and smart work and analyze the benefits of

  4. #4 peak

    sequence classification, and web content classification.⏎Reinforcement machine learning⏎A reinforcement learning algorithm, or agent, learns by interacting with its environment. In reinforcement learning, there is no answer in the data but the reinforcement agent decides what to do to

  5. #5 peak

    exploited⏎What is a narrative therapy?⏎Narrative therapy is a style of therapy that helps people become—and embrace being—an expert in their own lives In narrative therapy, there is an emphasis on the stories we develop and carry with us through our lives

  6. #6 peak

    look at some of the specific foods that are considered clean and maybe some simple recipes using foods with which we’re already familiar.⏎Tomorrow<|endoftext|>In this Artificial intelligence Essay, we will learn about Artificial intelligence, Types of Artificial Intelligence & Applications of Artificial Intelligence

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 if: "Let—let—let—let—let—let—let—let—let—let—let—let—let—let—let—let—let—let—let—let—let—let—

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

    tray' and covering it with paper.⏎My cousin was 24 years old on Friday April 5th in 1974. On what day⏎of the week was she born?⏎A tetromino is made up of

  2. #2 peak

    . The historic school house, built in 1872, still stands.⏎A historical marker at Cherry Creek provides additional information:⏎"Here, at one time, was the largest town in White Pine County. Part of the Cherry Creek Mining

  3. #3 peak

    framework you use to set goals, taking the time to plan what you want to achieve can make the difference to obtain what you want. Sort of if you know where you are going, you’ll get there. Otherwise, you may end up in

  4. #4 peak

    are, how you move, it can measure sound, light intensity and so on. Combine this with other data such as your email and social media activity and over time we can build a picture to help identify potential triggers 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. L15:853 strongly suppresses
  2. L10:931 excites
  3. L11:949 excites
  4. L4:1750 suppresses
  5. L9:361 excites
  6. L10:289 excites
  7. L6:502 suppresses
  8. L3:681 suppresses
  9. L9:2442 suppresses
  10. L6:2233 excites
  11. L4:1179 excites
  12. L12:962 suppresses
  13. L6:2843 suppresses
  14. L1:2751 suppresses
  15. L5:976 suppresses
  16. L4:1834 suppresses unclear: time spans and 'once you've'
  17. L5:224 excites
  18. L6:1829 suppresses
  19. L15:3010 excites
  20. L0:2135 suppresses
  21. L6:327 weakly suppresses
  22. L15:2521 weakly excites
  23. L11:1098 weakly excites
  24. L10:371 weakly suppresses

Feeds later layers

  1. L17:2162 excites
  2. L17:1845 excites
  3. L17:3069 excites
  4. L17:1201 excites
  5. L17:2238 excites
  6. L17:2213 excites
  7. L18:509 excites
  8. L17:472 suppresses
  9. L22:689 excites comma closing an intro clause
  10. L17:2524 suppresses
  11. L22:2294 excites
  12. L19:1982 excites
  13. L18:867 excites
  14. L19:2397 excites
  15. L19:2103 excites
  16. L17:2659 excites
  17. L19:1953 excites
  18. L17:2766 excites
  19. L17:2816 excites
  20. L18:1811 suppresses 'and' linking two descriptive claims
  21. L22:1124 excites
  22. L18:1246 weakly suppresses
  23. L20:242 weakly suppresses
  24. L17:1662 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 -2.02 and -1.592 values between -1.59 and -1.1650 values between -1.16 and -0.721126 values between -0.72 and -0.292553 values between -0.29 and 0.14105 values between 0.14 and 0.5824 values between 0.58 and 1.0116 values between 1.01 and 1.444 values between 1.44 and 1.883 values between 1.88 and 2.313 values between 2.31 and 2.743 values between 2.74 and 3.185 values between 3.18 and 3.612 values between 3.61 and 4.041 values between 4.04 and 4.481 values between 4.91 and 5.341 values between 5.34 and 5.781 values between 6.21 and 6.641 values between 6.64 and 7.081 values between 7.51 and 7.941 values between 8.81 and 9.241 values between 9.67 and 10.111 values between 10.11 and 10.541 values between 14.87 and 15.31offnegativepositiveoften

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. 一切都
  2. %"><
  3. família
  4. heads
  5. 你不
  6. 一切都是
  7. ausal
  8. >Main
  9. matter
  10. 我们将

Suppresses

  1. 者
  2. 提醒
  3. eming
  4. 在他
  5. тор
  6. tics
  7. 欢迎
  8. り
  9. 让她
  10. 支持