Neuron Explorer

Qwen3-0.6B

cycles and periods, before the word 'cycle'

A neuron in layer 22 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron responds to talk about repeating cycles, such as tides, moon phases, seasons and sleep rhythms, especially at the spot where the word 'cycle' would come next. When it was turned up, the model kept writing the word 'cycle' over and over.

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

    current. In an AC circuit, the voltage and current vary continuously with time. Let us first calculate the power at an instant and then it is averaged over a complete cycle.⏎The alternating voltage and alternating current in the series RLC circuit at an

  2. #2 peak

    . These charged particles collide with gas molecules in the atmosphere. The energy released in these collisions is given off as light.⏎Geomagnetic storms follow the 11-year solar

  3. #3 peak

    , it’s our phones, TVs, and laptops that are impairing our sleep.⏎In healthy adults, our biological clock follows a 24-hour wake-sleep cycle. As the sun rises and daylight gradually enters through the curtains, the body

  4. #4 peak

    .<|endoftext|>In ancient China one’s Zodiac sign was fixed by the position of the planet Jupiter during the year of one’s birth (it takes twelve years for Jupiter to orbit the sun). On this level, Ai Weiwei Circle of Animals/Zodiac

  5. #5 peak

    all still reading this post, right?⏎Well, let’s start off with a bit of backstory: For generations, a woman’s monthly cycle has been tied to the moon cycle likely because they’re about the same length–with a “typical

  6. #6 peak

    repeating event per unit time. It is also referred to as temporal frequency, which emphasizes the contrast to spatial frequency and angular frequency. The period is the duration of one cycle in a repeating event, so the period is the reciprocal of the frequency.⏎

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 can only be a good agent on a first- and second- or third-mention key to a particular problem at a particular time. I can only be a good agent when I have a good number of other agents at work 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

    laws of physics and chemistry (a mixture of chance and necessity or "natural law") and not by design. This is the naturalistic explanation. Darwinism (evolution based on the hypothesized natural selection of random mutations) is the mechanism that

  2. #2 peak

    chance of failing to pass on a beneficial mutation ).⏎As noted elsewhere (see ‘Giving up on reality’), Lenski seemed to have given up on ‘evolution in the lab’ and resorted to<|endoftext|>Paul McCartney heard the melody to

  3. #3 peak

    herbs,shrubs,trees). Animals were grouped according to their habitat and physical differences. The problem with this system was it did not group organisms into their evolutionary history.⏎How did Aristole classify life? What was the problem with his system

  4. #4 peak

    claims:⏎‘Lenski’s experiment is also yet another poke in the eye for anti-evolutionists, notes Jerry Coyne, an evolutionary biologist at the University of Chicago

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. L21:1710 excites
  2. L19:3004 suppresses
  3. L16:2979 suppresses
  4. L18:1837 suppresses
  5. L12:1879 excites
  6. L8:2650 excites
  7. L10:1707 suppresses
  8. L9:2310 suppresses
  9. L12:2912 suppresses
  10. L10:2870 suppresses
  11. L17:1571 excites
  12. L9:2937 excites
  13. L18:1157 excites
  14. L18:1149 suppresses
  15. L20:2982 excites
  16. L11:2586 suppresses
  17. L11:350 excites
  18. L15:2543 weakly excites
  19. L19:562 weakly excites
  20. L9:2069 weakly suppresses
  21. L17:2600 weakly excites
  22. L12:2782 weakly suppresses
  23. L15:1829 weakly excites
  24. L21:2065 weakly excites

Feeds later layers

  1. L26:2155 excites
  2. L23:2078 excites
  3. L23:2557 excites
  4. L27:2128 excites
  5. L26:2396 excites
  6. L24:2394 excites
  7. L25:1915 excites
  8. L27:3070 weakly excites
  9. L27:495 weakly excites
  10. L24:906 weakly excites
  11. L24:814 weakly excites
  12. L25:2678 weakly excites
  13. L23:2496 weakly excites
  14. L27:2304 weakly excites
  15. L24:89 weakly excites
  16. L25:3037 weakly excites
  17. L27:3046 weakly excites
  18. L26:519 weakly excites
  19. L26:1448 weakly excites
  20. L26:1862 weakly excites
  21. L26:1400 weakly excites
  22. L25:1558 weakly excites
  23. L25:2505 weakly excites
  24. L26:1001 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.

1 values between -7.97 and -7.203 values between -5.66 and -4.896 values between -4.89 and -4.125 values between -4.12 and -3.3510 values between -3.35 and -2.586 values between -2.58 and -1.8137 values between -1.81 and -1.04746 values between -1.04 and -0.272662 values between -0.27 and 0.50302 values between 0.50 and 1.2751 values between 1.27 and 2.0422 values between 2.04 and 2.8118 values between 2.81 and 3.5713 values between 3.57 and 4.346 values between 4.34 and 5.118 values between 5.11 and 5.885 values between 5.88 and 6.652 values between 6.65 and 7.422 values between 7.42 and 8.192 values between 8.96 and 9.731 values between 22.04 and 22.81offnegativepositiveoften

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. cycle
  2. cycles
  3. Cycle
  4. cycle
  5. Cycle
  6. cycles
  7. _cycle
  8. 周期
  9. -cycle
  10. 循环

Suppresses

  1. Katz
  2. 墒
  3. VIDIA
  4. Hearts
  5. marg
  6. 觚
  7. arrass
  8. ancias
  9. Proud
  10. Disabilities