Neuron Explorer

Qwen3-0.6B

'of' after a number or amount

A neuron in layer 0 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 responds to the word 'of' when it follows a number or measurement, like '22 of them' or '1/2 of'. The steered outputs did not show a clear effect tied to this pattern.

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

    385 of oats; 103,434 of wheat; 88

  2. #2 peak

    = 2 x 1/4 or 1/4 is 1/2 of 1/2<|endoftext|>Messier 52 (also known as M

  3. #3 peak

    1/500 of a second, the PWM output will produce a pulse. The length of this pulse

  4. #4 peak

    .6 square miles (250 km2) of it is land and 0.6 square miles (1.6 km2

  5. #5 peak

    requires only around 3.5-5 kWh/m3 of electricity.⏎According to the International Renewable Energy Agency (IRENA), desalination

  6. #6 peak

    0 with 997 athletes (22 of them women) from 24 countries competing in 95 events. 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: The question is, how do you make a sound in a way that you can make a sound of a certain kind of music that is a certain kind of a music. So I have to think about this. I'm not sure if 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

    most efficient level of power for the system in place.⏎<|endoftext|>Serious diseases, including diabetes, cancer, and eating disorders, can manifest as signs and symptoms inside of the mouth.⏎Learn what those dental words mean.⏎Get dental news feeds delivered directly

  2. #2 peak

    . Many students considering out-of-state colleges also take the SAT. The state only receives statewide score reports. For

  3. #3 peak

    comprehend the techniques; members of instructions want a step-by-step guide to enable them to perform some techniques.⏎Etymology is a well-known way to initiate meanings out-of acronyms, which happen to be abbreviations noticable due to the fact

  4. #4 peak

    way of looking at things. This should be obvious, because they are seeing *everything* from a different perspective. For example, when we think seeing the inside of an important component would be exciting and informative, they consider it a threat to their

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

None: this is the first layer.

Feeds later layers

  1. L19:378 excites
  2. L2:1640 weakly suppresses
  3. L3:1760 weakly suppresses
  4. L18:350 weakly suppresses
  5. L18:2227 weakly suppresses
  6. L25:2286 weakly suppresses
  7. L19:620 weakly excites
  8. L21:1452 weakly suppresses
  9. L5:1340 weakly suppresses
  10. L5:2888 weakly suppresses
  11. L7:1856 weakly excites
  12. L3:1259 weakly suppresses
  13. L2:847 weakly suppresses
  14. L21:11 weakly excites
  15. L5:2576 weakly suppresses
  16. L2:576 weakly excites
  17. L21:2 weakly excites
  18. L12:2312 weakly excites
  19. L7:2792 weakly excites
  20. L23:1863 weakly suppresses
  21. L7:710 weakly suppresses
  22. L13:2765 weakly excites
  23. L24:1655 weakly suppresses
  24. L4:3069 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 -1.01 and -0.951 values between -0.95 and -0.891 values between -0.89 and -0.834 values between -0.83 and -0.771 values between -0.71 and -0.654 values between -0.65 and -0.595 values between -0.59 and -0.537 values between -0.53 and -0.4716 values between -0.47 and -0.4126 values between -0.41 and -0.3526 values between -0.35 and -0.2953 values between -0.29 and -0.2368 values between -0.23 and -0.17152 values between -0.17 and -0.11438 values between -0.11 and -0.051355 values between -0.05 and 0.011106 values between 0.01 and 0.07418 values between 0.07 and 0.13153 values between 0.13 and 0.1945 values between 0.19 and 0.2513 values between 0.25 and 0.314 values between 0.31 and 0.372 values between 0.37 and 0.432 values between 0.43 and 0.491 values between 0.49 and 0.552 values between 0.61 and 0.672 values between 0.67 and 0.731 values between 1.21 and 1.271 values between 1.33 and 1.39offnegativepositiveoften

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. ��
  2. .Call
  3. _Service
  4. faction
  5. quence
  6. iore
  7. 习近
  8. .imwrite
  9. 各样
  10. 洑

Suppresses

  1. azes
  2. enna
  3. izzes
  4. dez
  5. agog
  6. quez
  7. 告诉大家
  8. 告知
  9. giveaway
  10. 告诉