Neuron Explorer

Qwen3-0.6B

"of" after a time or place noun

A neuron in layer 6 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 weakly on the word "of" after a time phrase like "in the year of", "the time of" or "the month of". It is a weak signal, and turning it up gave unrelated text, so the steering doesn't show the same idea.

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

    the result of an intense source of energy as the body passed through the cloth, perhaps at the moment of resurrection,” reported The Guardian.⏎Believed to be shroud of Jesus⏎The

  2. #2 peak

    . The title of the story is kept by the name of the village only. So the title truly signifies the story.⏎Born on November 8 in the year of 1908 Raja Rao was a famous writer. The place was

  3. #3 peak

    -old, who is an Electrical Engineer from Usha Rama College of Engineering and Technology, Vijayawada.⏎The product was to be launched in the month of May<|endoftext|>Scientists saw the Earth from a new perspective on 24th October

  4. #4 peak

    environment.⏎Despite that good news, the study further concluded that deaths in the year of the study publication would be in excess of 300,000.

  5. #5 peak

    hearts or arteries preserved enough to study. Of those, nine had evidence of blockage from atherosclerosis. “This disease has been around since before the time of Moses,” said Randall Thompson

  6. #6 peak

    received his Undergraduate and Master 's degrees. After receiving his degrees he became a faithful lawyer and was chosen to help draft the Declaration of Independence in the year of 1774 while also serving on the first Continental Congress. In the

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 want to have a system where the user can use a system where the following equation is given: (x + y + z) = (x + 1) * y * z. What is the name of the system that 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

    gdalin. Amygdalin is a plant compound that contains sugar and produces hydrogen cyanide. Hydrogen cyanide is thought to be the main anticancer compound formed from laetrile when broken

  2. #2 peak

    alin. Amygdalin is a chemical ingredient found in the pits of many fruits, raw nuts, and plants (see Question 1).⏎- Hydrogen cyanide is thought to be the main anticancer compound formed from laetrile when broken

  3. #3 peak

    of concern have been rising in atmospheric concentrations over the last two hundred or so years, since the beginning of the industrial age.⏎Those involved are methane, nitrous oxide, fluorocarbons, sulphur hexafluor

  4. #4 peak

    simply our way of life today: carbon dioxide, methane, nitrous oxide, hydrofluorocarbons, perfluoroc<|endoftext|>Nowadays,

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. L5:96 weakly suppresses
  2. L4:330 weakly suppresses
  3. L4:2049 weakly suppresses
  4. L1:369 weakly excites
  5. L1:2648 weakly excites
  6. L2:2965 weakly suppresses
  7. L3:2787 weakly excites
  8. L1:1055 weakly excites
  9. L0:2893 weakly suppresses
  10. L3:987 weakly suppresses
  11. L4:2632 weakly excites
  12. L0:2928 weakly suppresses
  13. L2:388 weakly suppresses
  14. L2:2498 weakly excites
  15. L2:1103 weakly excites
  16. L5:1075 weakly excites
  17. L3:348 weakly excites
  18. L4:1801 weakly excites
  19. L2:1899 weakly excites
  20. L1:1229 weakly excites
  21. L3:1877 weakly excites
  22. L4:52 weakly excites
  23. L4:2798 weakly suppresses
  24. L2:1469 weakly excites

Feeds later layers

  1. L7:1882 excites
  2. L8:333 excites
  3. L7:2687 weakly excites
  4. L18:217 weakly suppresses
  5. L25:669 weakly excites
  6. L11:157 weakly excites
  7. L21:2251 weakly excites
  8. L19:776 weakly excites
  9. L10:2838 weakly excites
  10. L16:1422 weakly excites
  11. L25:1695 weakly excites
  12. L20:585 weakly excites
  13. L8:2051 weakly excites
  14. L25:756 weakly excites
  15. L27:610 weakly suppresses
  16. L24:1526 weakly excites
  17. L27:1448 weakly suppresses
  18. L10:1148 weakly excites
  19. L24:1716 weakly excites
  20. L24:713 weakly excites
  21. L19:1691 weakly suppresses 'the' inside a phrase, mid-sentence
  22. L24:1693 weakly excites
  23. L22:43 weakly suppresses
  24. L9:758 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 -1.03 and -0.934 values between -0.93 and -0.843 values between -0.84 and -0.745 values between -0.74 and -0.647 values between -0.64 and -0.556 values between -0.55 and -0.4521 values between -0.45 and -0.3563 values between -0.35 and -0.26217 values between -0.26 and -0.16545 values between -0.16 and -0.061610 values between -0.06 and 0.03901 values between 0.03 and 0.13343 values between 0.13 and 0.23112 values between 0.23 and 0.3233 values between 0.32 and 0.4210 values between 0.42 and 0.5210 values between 0.52 and 0.615 values between 0.61 and 0.713 values between 0.71 and 0.813 values between 0.81 and 0.902 values between 0.90 and 1.001 values between 1.10 and 1.191 values between 1.19 and 1.291 values between 2.74 and 2.83offnegativepositiveoften

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. Wien
  2. Natal
  3. conver
  4. .AddDays
  5. -Pacific
  6. noon
  7. 收敛
  8. 氚
  9. Advent
  10. ather

Suppresses

  1. elling
  2. этому
  3. icers
  4. 依法追究
  5. 一堆
  6. legate
  7. гляд
  8. 四大
  9. 一枚
  10. 两张