Neuron Explorer

Qwen3-0.6B

'of' after 'that' in comparisons

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 on the word 'of' when it follows 'that' or a similar word to compare two things, as in 'similar to that of a gas'. Steering did not clearly change the topic, so what it does beyond this comparison habit is not certain.

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

    ___ in the United States and, until the beginning of the 20th century, was used by nearly all American cities. Its structure is similar to that of the ___2___ and national governments, with an elected mayor as chief of the

  2. #2 peak

    or plants that has characteristics of both parents; hybrid.⏎- A mule is a cross between a horse and

  3. #3 peak

    , but in one’s chest, one’s hands, and one’s feet, all together.”⏎Long describes Homer’s overall style to be that of ‘sensuous immediacy’, writing: ‘Homer delights in the vibr

  4. #4 peak

    Black Brant used in this case was a 4-stage rocket. As it separated the radar pattern matched that of a ballistic missile with multiple re-entry warheads coming down, further convincing the Russians

  5. #5 peak

    not provide mechanical properties that match that of healthy bone.⏎Nanobiocom developed an intelligent material made of bioactive components

  6. #6 peak

    The presence of charged ions means that a plasma is highly electrically conductive and responds strongly to magnetic and electric fields. Its behavior is most comparable to that of a gas, as the plasma has no defined volume but instead assumes the volume of

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 main idea of this problem is to find the area of the region of the set of points in the complex plane such that $z = e^{i k} $, where $k=2$ and the equation $z^2

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

    remember, and there is where a curriculum might come in handy. You can organize your lessons by setting up a program for your studies yourself, or acquiring all the necessary information from websites like https://growcurriculum.org/ and customizing it to

  2. #2 peak

    responsible adult is present in the home when the homebound teacher is working with the student. The parents must also make every effort to keep homebound instruction appointments as scheduled.<|endoftext|>“Anyone

  3. #3 peak

    disabilities. With almost 85% of adults and 96% of children visiting a medical professional each year, healthcare providers should be better equipped with the necessary knowledge and skills to provide high-quality healthcare to all

  4. #4 peak

    who would betray Him. He had already sealed the deal in verses 14-16. Judas asked Christ<|endoftext|>Treating Developmentally Disabled With Dual Diagnosis of Dementia or Alzheimer’s Disease⏎Alzheimer’s Disease is a leading cause

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. L5:2517 weakly suppresses
  2. L5:1732 weakly excites
  3. L3:1741 weakly excites
  4. L4:149 weakly suppresses
  5. L1:2143 weakly suppresses
  6. L4:2987 weakly suppresses
  7. L4:1375 weakly excites
  8. L3:1992 weakly excites
  9. L4:2180 weakly excites
  10. L3:2147 weakly excites
  11. L1:1092 weakly excites
  12. L5:2714 weakly suppresses
  13. L2:2229 weakly suppresses
  14. L2:2307 weakly suppresses
  15. L3:189 weakly excites
  16. L4:1034 weakly suppresses
  17. L2:2587 weakly suppresses
  18. L4:1330 weakly suppresses
  19. L1:1788 weakly excites
  20. L4:2922 weakly excites
  21. L5:2719 weakly excites
  22. L4:1210 weakly excites
  23. L5:1601 weakly excites
  24. L4:1484 weakly excites

Feeds later layers

  1. L15:1496 excites
  2. L12:1915 excites
  3. L13:2812 excites
  4. L14:2163 excites
  5. L9:1995 excites
  6. L21:2666 weakly excites
  7. L14:1795 weakly suppresses
  8. L14:2243 weakly excites
  9. L11:2109 weakly excites
  10. L9:264 weakly excites
  11. L13:1954 weakly excites
  12. L11:2336 weakly excites
  13. L12:1200 weakly excites
  14. L15:2730 weakly excites
  15. L12:1518 weakly excites
  16. L15:570 weakly excites
  17. L9:1558 weakly excites
  18. L15:3053 weakly suppresses
  19. L14:1013 weakly excites
  20. L11:1040 weakly suppresses
  21. L12:2692 weakly excites
  22. L9:2332 weakly excites
  23. L15:2219 weakly suppresses
  24. L12:1395 weakly excites 'as' in 'as ... as' comparisons

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 -1.96 and -1.811 values between -1.19 and -1.044 values between -1.04 and -0.883 values between -0.88 and -0.733 values between -0.73 and -0.5710 values between -0.57 and -0.4289 values between -0.42 and -0.26548 values between -0.26 and -0.111891 values between -0.11 and 0.051072 values between 0.05 and 0.20220 values between 0.20 and 0.3534 values between 0.35 and 0.518 values between 0.51 and 0.663 values between 0.66 and 0.823 values between 0.82 and 0.975 values between 0.97 and 1.132 values between 1.13 and 1.284 values between 1.28 and 1.441 values between 1.44 and 1.591 values between 1.59 and 1.742 values between 2.21 and 2.362 values between 2.52 and 2.671 values between 4.06 and 4.22offnegativepositiveoften

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. tridge
  2. Bail
  3. attribute
  4. 需要用到
  5. recognizable
  6. attributes
  7. require
  8. bail
  9. characteristic
  10. ируется

Suppresses

  1. anje
  2. менно
  3. 不然
  4. WAY
  5. راف
  6. andom
  7. 增
  8. affles
  9. kiệm
  10. jeta