Neuron Explorer

Qwen3-0.6B

"is" after "it" in advice phrasing

A neuron in layer 10 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 verb right after a dummy "it" in advice sentences, such as "it is important," "it is best" or "it pays to." It is usually the word just before a judgement about what to do. Turning it up gave mostly unrelated text, so the steering doesn'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

    Higher performance video cards provide smoother full motion video and better 3D gaming performance.⏎How Video Cards Operate⏎Before selecting a video card, we believe it is important to know what a video card does in the system. The separate video card

  2. #2 peak

    a unique continental and leading agricultural product. One of the countries on the equator line benefits from its climate and agriculture production. Before you go further, it is good for you to enrich your agriculture production countries here. Now, let’s get

  3. #3 peak

    You can communicate a thought, but your thought may not be understood. In some cases, your thought may not even reach the proper target. Thats why it pays to ask questions to make certain that people understand what you are saying. The great

  4. #4 peak

    the appSettings element and other configuration sections that a developer might define. It then looks in the application configuration file. To keep the machine configuration file manageable, it is best to put these settings in the application configuration file. However, putting the settings

  5. #5 peak

    point so that different grouped assemblies could be aligned according to their alignment points, thus aiding in mating parts together.⏎Third: Align to Center or Outside! It would be nice to align the center or outside edge of one object to the edge of another

  6. #6 peak

    potential that the technologies suggest. Potential that deserves to be explored and brought to market.⏎Before addressing the potential impact of the research and the responses to it, it makes sense to

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 am going to be part of a group. I have been going through a phase of decision-making, and I am going through a phase of decision-making. I have been going through a phase of decision-making, and I have been going

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

    1991. As Dr. Wade Huntley puts it:⏎According to this view, had it not been for a tendency toward wild-eyed anti-communism on the American side, the

  2. #2 peak

    , and I will be your God, and you will be My people; and you will walk in all the way which I command you, that it may be well with you.'⏎Matthew 7:24-27 “Therefore everyone who

  3. #3 peak

    students to shine through, I feel like I may have caught a glimpse of that, yet it was fleeting. My next steps are to reflect on what it was about the CSI routine that brought that thinking out.<|endoftext|>GNU Octave is a high

  4. #4 peak

    .tandfonline.com/pricing/journal/VECE20|⏎When requesting a correction, please mention this item's handle: RePEc:taf:jeduce:v:42:y:2011:i:2

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. L5:1885 strongly excites
  2. L5:1807 suppresses
  3. L4:636 suppresses
  4. L9:2252 suppresses
  5. L6:572 suppresses
  6. L9:1243 suppresses
  7. L9:1907 excites
  8. L6:2010 excites
  9. L7:1833 suppresses
  10. L5:478 weakly suppresses
  11. L6:1922 weakly excites
  12. L7:1970 weakly suppresses
  13. L7:2106 weakly suppresses
  14. L7:31 weakly suppresses
  15. L6:13 weakly excites
  16. L6:1829 weakly suppresses
  17. L7:1469 weakly excites "(" before a year in citations
  18. L4:2583 weakly suppresses
  19. L8:10 weakly excites
  20. L2:2648 weakly suppresses
  21. L4:1320 weakly excites
  22. L2:2193 weakly excites
  23. L9:2056 weakly excites
  24. L7:1163 weakly suppresses

Feeds later layers

  1. L17:1773 excites
  2. L13:645 excites
  3. L12:1022 suppresses
  4. L13:2186 suppresses
  5. L14:534 suppresses
  6. L11:1046 suppresses
  7. L11:2158 excites
  8. L12:850 suppresses
  9. L18:2546 excites
  10. L13:921 excites
  11. L12:525 excites
  12. L13:720 suppresses
  13. L13:1228 excites
  14. L14:1309 excites
  15. L11:2956 suppresses
  16. L16:2102 excites
  17. L15:1973 suppresses
  18. L17:503 excites
  19. L15:2636 weakly suppresses
  20. L15:1092 weakly excites
  21. L16:1100 weakly excites
  22. L18:727 weakly suppresses
  23. L14:1062 weakly suppresses
  24. L16:1985 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.

145 values between -0.81 and -0.442298 values between -0.44 and -0.071425 values between -0.07 and 0.3014 values between 0.30 and 0.676 values between 0.67 and 1.046 values between 1.04 and 1.411 values between 1.41 and 1.781 values between 1.78 and 2.152 values between 2.52 and 2.902 values between 2.90 and 3.271 values between 3.27 and 3.641 values between 4.01 and 4.381 values between 4.75 and 5.121 values between 5.12 and 5.492 values between 6.61 and 6.981 values between 9.20 and 9.571 values between 13.65 and 14.02offnegativepositiveoften

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. fact
  2. łość
  3. окумент
  4. learn
  5. WARE
  6. empo
  7. ách
  8. 釜
  9. 隆
  10. ruc

Suppresses

  1. 捺
  2. 主要包括
  3. positions
  4. coverage
  5. ,default
  6. الداخلية
  7. atable
  8. бу
  9. itself
  10. ittance