Neuron Explorer

Qwen3-0.6B

"your" addressing the reader

A neuron in layer 8 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 "your" when a sentence speaks directly to the reader, as in "If your kitten..." or "Is your person...". It reacts in the opposite direction to third-person possessives like "its", "his" and "'s". Turning it up did not produce obviously related text.

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens an email to the maker with the neuron already filled in).

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

    Kitten? How Do I Tell a Kitten’s Age?⏎If your kitten is yet to get its adult teeth, it is relatively easier to guess its

  2. #2 peak

    cancer. Whether triggered by an event or by one's own biochemistry, depression involves changes in the brain's neurotransmitter system. If you have ever had your mood altered by a drug, you know that how you feel is not simply a

  3. #3 peak

    in the Bible⏎In the morning they arose early and exchanged oaths; then Isaac sent them away and they departed from him in peace.⏎And if one man's ox does damage to another man's ox, causing its death, then the living

  4. #4 peak

    by By Dr. Carolyn K. Stratz⏎Q: My kids get their vaccinations - what about me?⏎A: Back-to-school time doesn't just mean

  5. #5 peak

    to the death over territory or a superior shell. Impact injuries, such as falls and being dropped, can lead to death.⏎What happens when crab die?⏎If your hermit crab dies, it will begin to decompose – and its

  6. #6 peak

    sports require an exorbitant amount<|endoftext|>Guess Who? Identity theft?⏎“Does your person have blue eyes?” “Does your person have massive eyebrows?” “Is your person wearing a hat?” “Is your person Frank?”⏎I was playing Guess

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 an old idea of building a model to simulate the environment of the future. To achieve this, I have an old idea of building a model to simulate the environment of the future. To achieve this, I have an old idea of

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

    , „Washington Allston brought his enthusiasm for art and for romanticism into the very environment that needed them most and cared for them least. That was Allston's glory. That was Allston's tragedy.⏎Allston set up a studio in

  2. #2 peak

    – a majority of the garbage is comprised of tiny bits of plastic, barely visible to the human eye. Due to the small size of much of the garbage and its location floating 10 feet beneath the ocean’s surface, the garbage patch does

  3. #3 peak

    standstill, leaving, for a short period, the land open for God’s people to take over.⏎Special thanks to Dr. Robert L Diss Jr. for his materials on this

  4. #4 peak

    astronauts Jim McDivitt and Ed White — conducted scientific experiments, including photography of Earth’s weather and terrain, for the remainder of their four-day mission following White’s historic first American

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. L4:217 suppresses
  2. L6:1233 suppresses
  3. L7:111 suppresses
  4. L5:1747 suppresses
  5. L5:125 excites "of" after all three, both, ten
  6. L4:300 excites
  7. L5:2275 excites
  8. L6:972 excites "well" after "how"
  9. L7:93 excites
  10. L5:53 excites
  11. L4:2853 excites
  12. L3:1318 weakly suppresses
  13. L4:2473 weakly excites
  14. L7:8 weakly excites
  15. L6:1718 weakly suppresses
  16. L7:2164 weakly suppresses period inside country abbreviations
  17. L4:1471 weakly excites
  18. L1:2550 weakly suppresses
  19. L6:1195 weakly excites
  20. L7:304 weakly excites
  21. L4:698 weakly suppresses
  22. L7:1853 weakly suppresses
  23. L1:2074 weakly suppresses
  24. L5:533 weakly excites

Feeds later layers

  1. L14:313 excites
  2. L9:1903 suppresses
  3. L11:3015 excites
  4. L15:448 excites
  5. L9:143 excites
  6. L15:2005 excites
  7. L16:940 suppresses
  8. L10:815 suppresses
  9. L14:1601 weakly excites
  10. L14:2150 weakly excites
  11. L19:238 weakly suppresses
  12. L16:1382 weakly excites comma after an introductory phrase
  13. L12:238 weakly suppresses
  14. L9:266 weakly excites
  15. L13:1099 weakly suppresses
  16. L13:1376 weakly excites
  17. L17:2792 weakly suppresses
  18. L15:1234 weakly suppresses
  19. L9:288 weakly excites
  20. L17:1194 weakly suppresses
  21. L22:552 weakly suppresses
  22. L17:1959 weakly suppresses
  23. L16:559 weakly suppresses weak, mixed: verbs and adverbs in claims
  24. L13:909 weakly suppresses 'to' before a verb after a noun

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 -3.30 and -3.162 values between -2.35 and -2.211 values between -2.21 and -2.081 values between -2.08 and -1.942 values between -1.94 and -1.811 values between -1.54 and -1.406 values between -1.40 and -1.273 values between -1.27 and -1.132 values between -1.13 and -1.004 values between -1.00 and -0.8611 values between -0.86 and -0.7216 values between -0.72 and -0.5924 values between -0.59 and -0.4561 values between -0.45 and -0.32179 values between -0.32 and -0.18733 values between -0.18 and -0.051874 values between -0.05 and 0.09712 values between 0.09 and 0.22210 values between 0.22 and 0.3637 values between 0.36 and 0.497 values between 0.49 and 0.635 values between 0.63 and 0.764 values between 0.76 and 0.901 values between 0.90 and 1.043 values between 1.04 and 1.171 values between 1.17 and 1.314 values between 1.31 and 1.441 values between 1.44 and 1.581 values between 1.85 and 1.981 values between 1.98 and 2.12offnegativepositiveoften

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. liğinde
  2. enough
  3. 字号
  4. 好几个
  5. tle
  6. keyed
  7. Ngoại
  8. TimeString
  9. somebody
  10. cards

Suppresses

  1. eliness
  2. ament
  3. uel
  4. ugs
  5. \",⏎
  6. amel
  7. agascar
  8. �
  9. lust
  10. âm