Neuron Explorer

Qwen3-0.6B

reciprocal 'each other' or 'one another'

A neuron in layer 13 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 "other" or "another" in phrases like "each other" and "one another", which show people or things acting on each other. It is very clear in the examples. When turned up, the model's writing changed topic and did not stay on this idea.

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

    for a sentence to be grammatically correct, the subject and verb must both be singular or plural. In other words, the subject and verb must agree with one another in their tense. If the subject is in plural form, the verb should also

  2. #2 peak

    made available to customers using the web. This write-up briefly covers the different types of posting as well as goes over just how these different approaches differ from each various other and just how they can be useful for authors.⏎In a typical publisher-author partnership

  3. #3 peak

    Pharm.of or pertaining to drugs that interfere with one another chemically or physiologically and therefore cannot be mixed or prescribed together.⏎1

  4. #4 peak

    nutritional and / or pharmacological.⏎It is very important to note that in addition to external factors, nutritional or pharmacological substances can interact with each other due to its chemical and reactive (acid / base, oxidant / reducer etc

  5. #5 peak

    task in a foolish manner.⏎3. A father and his sons⏎A father had four sons. He loved them very much. They always used to help one another<|endoftext|>Ramses III, Ramses also spelled Ramesses or Rameses

  6. #6 peak

    linked may help you understand symptoms and manage them more effectively during this unsettling time.⏎How does it work? The brain and the body are constantly sending messages to each other. These messages tell the brain and body to make changes and adjustments to the way

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 am going to write up on the following: I will use the fact that I am going to be thinking about how to explain the fact that I am using a rectangle is like a square is like a rectangle, which is a triangle.

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

    a quiver of arrows conspicuously in your hall or library, and you will soon discover that no exquisite painting or bit of statuary will receive from guests more attention than will be accorded to these ancient weapons.⏎No doubt if one could procure

  2. #2 peak

    對 CNY 感興趣?⏎Early Currency in China⏎With a history of over 300

  3. #3 peak

    renimine MSÜ Barbaros DEBİM Enstitüsünde devam etmekte aynı zamanda enerji sistem ve modelleme üzerine araştırmalar yapmaktadır.<|endoftext|>- 10 to 15 minutes⏎

  4. #4 peak

    UNDS ARE THOSE ORGANIC COMPOUNDS WHICH HAVE BENZENE RING (CYCLOHEXA-1,3,5-TRIENE). AROMATIC COMPOUNDS ARE ALWAYS FOLLOWS

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. L12:2145 excites
  2. L7:361 excites
  3. L12:1410 suppresses
  4. L12:953 weakly suppresses
  5. L12:2687 weakly suppresses
  6. L6:628 weakly excites
  7. L6:2276 weakly suppresses
  8. L12:2422 weakly excites
  9. L1:564 weakly excites
  10. L0:505 weakly excites
  11. L8:230 weakly excites
  12. L12:902 weakly suppresses
  13. L9:1432 weakly excites
  14. L2:3005 weakly suppresses
  15. L7:1301 weakly suppresses
  16. L6:393 weakly suppresses
  17. L10:2578 weakly excites
  18. L3:2161 weakly excites
  19. L1:210 weakly excites
  20. L9:134 weakly suppresses
  21. L11:2329 weakly excites
  22. L5:763 weakly excites
  23. L6:2883 weakly suppresses
  24. L11:457 weakly suppresses

Feeds later layers

  1. L15:853 excites
  2. L16:2977 excites 'which' after a preposition
  3. L17:1080 excites
  4. L16:605 suppresses
  5. L15:3006 weakly suppresses
  6. L15:804 weakly suppresses
  7. L24:545 weakly excites
  8. L14:539 weakly excites
  9. L17:850 weakly suppresses
  10. L15:1614 weakly excites
  11. L14:1998 weakly excites
  12. L17:2162 weakly excites
  13. L17:421 weakly excites
  14. L16:1365 weakly excites
  15. L14:2854 weakly excites
  16. L16:507 weakly excites
  17. L18:1678 weakly excites
  18. L15:1744 weakly suppresses
  19. L17:2878 weakly excites
  20. L14:1552 weakly suppresses
  21. L15:2181 weakly excites
  22. L14:404 weakly excites
  23. L20:2318 weakly suppresses 'recent' in time phrases
  24. L24:691 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 -2.07 and -1.961 values between -1.53 and -1.421 values between -1.20 and -1.091 values between -0.87 and -0.762 values between -0.76 and -0.661 values between -0.66 and -0.5512 values between -0.55 and -0.4441 values between -0.44 and -0.33155 values between -0.33 and -0.22438 values between -0.22 and -0.111237 values between -0.11 and -0.001289 values between -0.00 and 0.11427 values between 0.11 and 0.22179 values between 0.22 and 0.3279 values between 0.32 and 0.4324 values between 0.43 and 0.549 values between 0.54 and 0.654 values between 0.65 and 0.762 values between 0.76 and 0.872 values between 0.87 and 0.981 values between 1.19 and 1.301 values between 1.52 and 1.631 values between 2.17 and 2.28offnegativepositiveoften

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. ending
  2. ine
  3. Hai
  4. ег
  5. esto
  6. 等级
  7. 这个
  8. audiences
  9. tics
  10. 端

Suppresses

  1. 公司将
  2. Sparse
  3. _sheet
  4. _MAY
  5. icense
  6. uniqu
  7. IMO
  8. Sparse
  9. baptized
  10. shape