Neuron Explorer

Qwen3-0.6B

the word "some" mid-sentence

A neuron in layer 16 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 "some" when it means something like "a certain" or "at some point," as in "some kind of" or "some software." Turning it up did not produce any obvious theme in the model's replies.

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

    Artemis mission.⏎The contract, which is worth $2.9 billion, means that a SpaceX vehicle will be responsible for putting humans back on the moon at some point this decade. It will be the first time the feat has been accomplished since

  2. #2 peak

    . The religion has spread across the world, claiming the devotion of nearly two thousand million people. Christians always have thought Jesus and the apostles’ age to be some kind of standard for all the other eras.⏎When it comes to Christianity,

  3. #3 peak

    to others can benefit your own wellbeing as much as it benefits those who receive your act of kindness?⏎It’s true. Research shows that helping others is associated with some serious psychological benefits. Generosity and giving back offer a multitude of benefits for our

  4. #4 peak

    all be dark and heavy. And if it had been in full daylight we’d all be so light. But He did this at dawn, so that we are some of each. Regarding the hadith

  5. #5 peak

    out of 100. Which may not sound like much.⏎But consider that 1 out of 15,000 kids gets cancer of some kind, and think about the attention and research and money devoted to understanding and treating

  6. #6 peak

    to yourself. For example, thinking that everything people do or say is some kind of reaction to you. You also compare yourself to others, trying to determine

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 use of a technology and the use of the technology to be used in any of the factors of a single equation to be determined, as the first of a number of factors which, the first of which to the last, as many as

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

    trip the circuit breaker.⏎Email Based, Online Homework Assignment Help in Classification Of Relays⏎Transtutors is the best place to get answers to all your doubts regarding classification of relays with examples. Transtutors has a vast panel of experienced

  2. #2 peak

    Social Cognition in Non-human Primates Using a Network of Computerized Automated Learning Device (ALDM) Test Systems⏎Institutions: Aix-Marseille University.⏎Fag

  3. #3 peak

    well as water. Try not to step on or dig in the soil when it is wet, because you can squeeze the oxygen out of it. If clay soil dries out too

  4. #4 peak

    Copy an existing data directory.⏎The following discussion provides more detail about each method.⏎Normally, you should never have two servers that update data in the same databases. This may lead to unpleasant surprises if your operating system does not support fault-free system locking

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. L10:388 weakly excites
  2. L6:1549 weakly excites
  3. L9:2690 weakly excites
  4. L0:1532 weakly excites
  5. L9:2958 weakly suppresses
  6. L15:81 weakly suppresses line breaks inside running text
  7. L2:1604 weakly suppresses
  8. L1:1039 weakly suppresses dash opening a bullet list item
  9. L3:1307 weakly suppresses
  10. L0:295 weakly excites
  11. L3:1954 weakly suppresses
  12. L11:122 weakly suppresses
  13. L1:1663 weakly excites
  14. L13:979 weakly suppresses
  15. L9:2827 weakly excites
  16. L1:2358 weakly suppresses
  17. L10:2490 weakly excites
  18. L1:2378 weakly excites
  19. L0:1409 weakly suppresses
  20. L4:1156 weakly excites
  21. L0:1664 weakly excites
  22. L4:1106 weakly suppresses
  23. L5:1252 weakly excites
  24. L6:609 weakly excites

Feeds later layers

  1. L27:1317 suppresses
  2. L20:1047 suppresses
  3. L17:2233 excites 'any' after negatives or 'more'
  4. L19:2522 suppresses
  5. L17:963 weakly suppresses
  6. L18:591 weakly suppresses
  7. L20:240 weakly excites
  8. L19:654 weakly excites
  9. L27:60 weakly excites
  10. L24:434 weakly suppresses
  11. L24:443 weakly suppresses
  12. L25:390 weakly excites
  13. L25:335 weakly suppresses
  14. L18:1379 weakly excites
  15. L18:1433 weakly suppresses
  16. L17:1706 weakly suppresses
  17. L18:81 weakly excites
  18. L26:111 weakly suppresses
  19. L17:1179 weakly excites
  20. L18:554 weakly suppresses
  21. L21:271 weakly excites
  22. L20:807 weakly suppresses
  23. L19:1180 weakly suppresses
  24. L25:377 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 -1.93 and -1.521 values between -1.52 and -1.1024 values between -1.10 and -0.69659 values between -0.69 and -0.282845 values between -0.28 and 0.14339 values between 0.14 and 0.5515 values between 0.55 and 0.967 values between 0.96 and 1.383 values between 1.38 and 1.794 values between 1.79 and 2.211 values between 2.62 and 3.031 values between 5.10 and 5.521 values between 5.93 and 6.342 values between 7.17 and 7.581 values between 8.41 and 8.831 values between 8.83 and 9.241 values between 12.96 and 13.381 values between 13.79 and 14.201 values between 14.20 and 14.62offnegativepositiveoften

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. iet
  2. 人家
  3. ilestone
  4. tility
  5. lưng
  6. ')]
  7. cretion
  8. 焰
  9. oralType
  10. udy

Suppresses

  1. normals
  2. negatives
  3. уч
  4. losures
  5. classes
  6. memberships
  7. alars
  8. сх
  9. .components
  10. aches