Neuron Explorer

Qwen3-0.6B

Rh blood type and related terms

A neuron in layer 9 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 is most sure about the phrase 'Rh' in blood type talk, and it also fires on a few scattered words like 'fake', 'trans fat', 'water' and 'planets'. It goes quiet or negative on word-game and spelling prompts. Turning it up did not bring back blood talk; the model drifted into temperature and repetition.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

    second bottle to be the fake.⏎In practice, there are some limitations to a manual application of this geometric analysis

  2. #2 peak

    , palm and coconut oils, sugary foods and beverages, saturated fat – found mostly in foods that come from animals; trans fat (trans fatty acids) – found in foods made with hydrogenated oils and fats, such

  3. #3 peak

    we expect the brown dwarf to have properties that are different from previously known brown dwarfs and much closer to those of giant exoplanets — it could even have water clouds in its atmosphere," the paper's lead author, Michael Liu of the University

  4. #4 peak

    others with type AB blood, but can receive blood from anyone.⏎Rh (+) positive blood means that your red blood cells have D antigens on their surface. Rh (-) negative blood means that your red blood cells do not have D antigens

  5. #5 peak

    all over the world. In Caucasians, the ratio of Rh (+) to Rh (-) blood is approximately 4.5:1,

  6. #6 peak

    , but it also determines your blood type. There are two main blood groups, the ABO group and the Rh group. The ABO group is made up of A, B, AB,

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 have a 4-digit number, and the number is 30% and 40% of the number. Also, I have a 10% and 10% of the number, and I have a

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

    ible furnace. Since argon or nitrogen is used as the refining medium, there is no pollution to<|endoftext|>Aptly named, the litte Owl. Guess what? The little owl is small!⏎The Little Owl is not native to Great Britain

  2. #2 peak

    to outdoor enthusiasts, such as hikers. JanSport sold all types of bags, from day packs to backpacks.⏎Whether you’re a<|endoftext|>- Enter a word for the dictionary definition.⏎From The Collaborative International Dictionary of English v.0

  3. #3 peak

    2⏎The word "focus" uses 5 letters: C F O S U.⏎No direct anagrams for focus found in this word list.⏎List shorter words within focus, sorted by length⏎All words formed from focus by changing one letter

  4. #4 peak

    , hatching into larvae within 24 to 48 hours after fertilisation (8).<|endoftext|>Peter Wadhams’ book title is a play on words from the famous Hemingway novel, as also is the last chapter of the

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. L6:757 excites
  2. L8:1948 excites
  3. L7:1103 suppresses 'as' in 'not as ... as' comparisons
  4. L8:843 weakly suppresses
  5. L0:1844 weakly suppresses
  6. L6:2227 weakly excites
  7. L6:2160 weakly excites
  8. L3:2204 weakly excites
  9. L8:647 weakly suppresses
  10. L6:2432 weakly excites
  11. L6:2273 weakly suppresses
  12. L7:1663 weakly suppresses
  13. L4:1921 weakly suppresses
  14. L6:732 weakly suppresses
  15. L6:1572 weakly suppresses
  16. L3:1765 weakly excites
  17. L7:1143 weakly suppresses
  18. L4:1741 weakly suppresses
  19. L7:2407 weakly excites
  20. L0:1556 weakly excites
  21. L6:1000 weakly suppresses
  22. L2:1623 weakly excites
  23. L3:2364 weakly suppresses
  24. L3:1904 weakly excites

Feeds later layers

  1. L18:1980 suppresses
  2. L21:1054 suppresses
  3. L12:2026 suppresses
  4. L12:2290 suppresses
  5. L11:2308 suppresses quantity words like 'some' and 'of'
  6. L12:2894 suppresses
  7. L17:1348 weakly suppresses
  8. L10:1555 weakly suppresses
  9. L12:2824 weakly suppresses
  10. L12:466 weakly suppresses
  11. L20:2455 weakly suppresses
  12. L10:2959 weakly excites
  13. L11:1213 weakly suppresses
  14. L13:1648 weakly suppresses
  15. L10:978 weakly suppresses
  16. L12:2514 weakly suppresses
  17. L24:1841 weakly suppresses
  18. L13:1846 weakly excites
  19. L24:1815 weakly suppresses
  20. L10:2835 weakly excites
  21. L14:1795 weakly suppresses
  22. L16:2718 weakly suppresses
  23. L10:1897 weakly suppresses
  24. L11:2978 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 -3.22 and -3.111 values between -2.38 and -2.282 values between -1.45 and -1.341 values between -1.34 and -1.241 values between -1.13 and -1.032 values between -1.03 and -0.933 values between -0.93 and -0.821 values between -0.82 and -0.722 values between -0.72 and -0.614 values between -0.61 and -0.5124 values between -0.51 and -0.4176 values between -0.41 and -0.30187 values between -0.30 and -0.20453 values between -0.20 and -0.09903 values between -0.09 and 0.01996 values between 0.01 and 0.11649 values between 0.11 and 0.22370 values between 0.22 and 0.32146 values between 0.32 and 0.4362 values between 0.43 and 0.5317 values between 0.53 and 0.635 values between 0.63 and 0.741 values between 0.74 and 0.841 values between 0.84 and 0.95offnegativepositiveoften

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. ropol
  2. iju
  3. .arraycopy
  4. yleft
  5. ipop
  6. ija
  7. 优势
  8. (push
  9. oha
  10. 从严治党

Suppresses

  1. crossword
  2. 谜
  3. 的事情
  4. Suffix
  5. spelling
  6. Regex
  7. 仨
  8. ständ
  9. uzzle
  10. spell