Neuron Explorer

Qwen3-0.6B

the word 'even' as emphasis

A neuron in layer 12 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 'even' when it adds emphasis or a surprise, as in 'even the most pessimistic' or 'don't even think about'. It is quiet on most other words. Turned up, the model's text wandered without a clear link to this word.

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

    timeframe⏎- Low: Prioritize and decide whether to<|endoftext|>Stunning new data not yet publicly released shows Louisiana losing its battle with rising seas much more quickly than even the most pessimistic studies have predicted to date.⏎While state officials continue to argue

  2. #2 peak

    days by a fraction, hardly had an impact on the planet in the long run. In fact, scientists have a hard time spotting the effect of even bigger quakes on something such as the Earth's rotation, said Richard Gross,

  3. #3 peak

    the Titanic, less than half survived. There were only 20 lifeboats aboard the White Star Line luxury ship, enough to carry half those onboard, but even these were not filled to capacity. When the liner Carpathia reached the disaster

  4. #4 peak

    cover stuff that well,” says Rapini, who was not involved in the research.⏎“Myself, personally, I’m a dermatologist, and I don’t even wear sunscreen all that much. I stay in the shade,” he says. “

  5. #5 peak

    9/11s every week for the last 7 years⏎, would you know which one I'm talking about?⏎I bet few westerners could, even though it's by far the deadiest conflict of the last 60

  6. #6 peak

    one’s mind around the concept of black holes. One teaspoon can be estimated to have tons and tons of weight. They are so dense that many times light cannot even escape. or at least that is what astronomers think. Are they right?⏎

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 is the use of the “S” in the name of the car? So, why is the name "Car" relevant? What is the “S” in the name? What is the “S” in the name? I

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

    exact cooking times for<|endoftext|>Here are the 15 types of distorted thinking:⏎1. Filtering: You take the negative details and magnify them, while filtering out all positive aspects of a situation. A single detail may be picked out, and

  2. #2 peak

    turn toward a more populist brand of politics has more to do with the energy of reform movements within Honduras itself, as well as throughout the rest of Latin America, than any personal awakening.⏎From the shift to civilian rule in 19

  3. #3 peak

    or policies of the West - chiefly the United States - were actually not very important. He implicitly affirms the idea that the Soviet Union fell to domestic factors, dismissing the idea that an external power could cause such domestic upheaval as "childish

  4. #4 peak

    causing the periphery to gradually fade away, not only will the photo be more like actual vision, it can immediately draw the eye to the main subject and away from unimportant elements in the background or periphery. It

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. L11:2083 suppresses
  2. L11:1095 suppresses
  3. L9:2535 suppresses
  4. L11:2937 excites
  5. L7:32 excites
  6. L9:1899 weakly suppresses
  7. L8:1962 weakly suppresses
  8. L4:151 weakly excites
  9. L9:54 weakly excites
  10. L7:662 weakly excites
  11. L8:2348 weakly excites
  12. L5:6 weakly suppresses
  13. L11:1006 weakly excites
  14. L5:45 weakly excites
  15. L6:1190 weakly excites
  16. L6:1175 weakly excites
  17. L10:2069 weakly excites
  18. L5:2058 weakly excites
  19. L11:2540 weakly excites
  20. L7:650 weakly excites
  21. L6:1477 weakly suppresses
  22. L4:9 weakly excites
  23. L0:653 weakly suppresses
  24. L4:2802 weakly excites

Feeds later layers

  1. L14:745 suppresses
  2. L20:952 suppresses
  3. L19:2606 suppresses
  4. L16:2401 suppresses
  5. L15:2954 suppresses
  6. L14:480 suppresses
  7. L13:2356 suppresses
  8. L18:825 suppresses 'as well as' and list connectors
  9. L14:1217 suppresses
  10. L14:2166 suppresses
  11. L16:1735 suppresses
  12. L14:651 suppresses
  13. L14:2882 suppresses
  14. L15:2455 suppresses
  15. L17:1539 suppresses
  16. L14:1859 weakly suppresses
  17. L16:686 weakly suppresses
  18. L16:964 weakly suppresses
  19. L16:2591 weakly suppresses
  20. L16:1282 weakly suppresses
  21. L17:1017 weakly suppresses
  22. L26:622 weakly excites
  23. L15:2205 weakly suppresses
  24. L15:2226 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.

1 values between -3.14 and -3.021 values between -3.02 and -2.901 values between -2.90 and -2.781 values between -2.29 and -2.171 values between -2.17 and -2.051 values between -2.05 and -1.931 values between -1.93 and -1.811 values between -1.69 and -1.571 values between -1.57 and -1.454 values between -1.45 and -1.333 values between -1.33 and -1.202 values between -1.20 and -1.082 values between -1.08 and -0.961 values between -0.96 and -0.843 values between -0.84 and -0.726 values between -0.72 and -0.6010 values between -0.60 and -0.4829 values between -0.48 and -0.36111 values between -0.36 and -0.23456 values between -0.23 and -0.111029 values between -0.11 and 0.011081 values between 0.01 and 0.13751 values between 0.13 and 0.25313 values between 0.25 and 0.3776 values between 0.37 and 0.4916 values between 0.49 and 0.612 values between 0.61 and 0.741 values between 0.74 and 0.862 values between 0.86 and 0.981 values between 1.58 and 1.71offnegativepositiveoften

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. lesh
  2. INESS
  3. 委组织部
  4. �
  5. сла
  6. scriber
  7. ishops
  8. 部副部长
  9. ович
  10. ицы

Suppresses

  1. 其他
  2. other
  3. 其它
  4. other
  5. 其余
  6. 其他的
  7. Other
  8. 其他国家
  9. andere
  10. Other