Neuron Explorer

Qwen3-0.6B

sentence end before a line break

A neuron in layer 12 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 when a sentence finishes and a new line or paragraph is about to start, especially after a full stop, exclamation mark or line break. Turning it up did not give a clear theme in the model's writing.

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

    the pumping and processing of natural gas, but there’s now a new means for preventing such, and it’s a lot more friendly to the environment and company budgets.⏎That’s right, Siftek. It’s the new name in natural gas

  2. #2 peak

    to alleviate stress and prioritize tasks that are manageable.⏎Feeling overwhelmed can occur at any point in life, but for many it’s always affected their studies or work⏎Suppose you regularly feel overwhelmed by the noise and hustle and bustle of crowded

  3. #3 peak

    verter is the analog spindle, and the spindle driven by the servo motor is the servo spindle. Both can meet the control requirements of CNC machine tool spindles.⏎With the development of technology in the field of

  4. #4 peak

    > Another example is to imagine a Tree in which the leaves contain⏎> "objects." If I want to change a property of one of those leaf objects,⏎You can't in general, the thing with a different property is a different⏎>

  5. #5 peak

    are too complex for a traditional factory to handle. In time, these amazing machines may be able to make almost anything, anywhere—from your garage to an African village.⏎The applications of 3D printing are especially

  6. #6 peak

    and 2).⏎Music National Curriculum for KS1⏎Key stage 1⏎Pupils should be taught to:⏎- use their voices expressively and creatively by singing songs and speaking chants and rhymes⏎- play tuned and untuned instruments

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 been in the car for 10 hours, and I have never seen any of the people who have driven on to the plane to take off to land in the airport in the morning for the first 30 minutes that the

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

    : Mining World⏎Population: 300 (Custodial staff)⏎Geography/Demography: Caligine II is a small moon orbiting the Gas Giant Caligine

  2. #2 peak

    of the month of Nisan, which coincides with a full moon.⏎Question: Is Passover the same time/date as Easter and are presents given?⏎Answer: Passover does not necessarily fall on the same date as Easter, though it usually

  3. #3 peak

    .⏎No direct anagrams for endoplasm found in this word list.⏎Words formed by adding one letter before or after endoplasm (in bold), or to adelmnops in any order:⏎s - endoplasms⏎All words

  4. #4 peak

    this area which could be gained from excavation of<|endoftext|>In which Scrabble dictionary does ZEATINS exist?⏎Definitions of ZEATINS in dictionaries:⏎- noun -⏎a chemical compound found in maize⏎There are 7 letters in ZE

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. L11:1527 excites
  2. L11:2971 excites
  3. L8:2520 suppresses
  4. L9:1743 excites
  5. L9:1949 suppresses
  6. L8:1848 excites
  7. L11:1619 suppresses
  8. L10:1169 weakly suppresses
  9. L10:471 weakly excites
  10. L11:2451 weakly suppresses
  11. L7:2303 weakly excites
  12. L9:257 weakly suppresses
  13. L8:579 weakly excites
  14. L10:280 weakly suppresses
  15. L10:1523 weakly excites
  16. L1:2067 weakly suppresses
  17. L5:560 weakly suppresses
  18. L0:2266 weakly excites
  19. L11:2928 weakly excites
  20. L11:1344 weakly suppresses
  21. L6:257 weakly excites
  22. L2:2997 weakly suppresses
  23. L11:1965 weakly excites
  24. L10:963 weakly suppresses

Feeds later layers

  1. L15:1785 excites
  2. L14:385 excites
  3. L14:1092 weakly excites
  4. L14:1648 weakly suppresses
  5. L14:209 weakly excites
  6. L13:1238 weakly excites
  7. L16:2969 weakly excites
  8. L15:1619 weakly excites
  9. L14:1178 weakly excites
  10. L15:502 weakly excites
  11. L19:1108 weakly excites 'your' or 'our' before a noun
  12. L18:3071 weakly suppresses
  13. L14:134 weakly excites spot right before a citation year
  14. L25:2335 weakly suppresses
  15. L17:2154 weakly excites
  16. L18:279 weakly suppresses
  17. L18:556 weakly excites
  18. L21:2213 weakly suppresses
  19. L17:1712 weakly excites
  20. L21:733 weakly suppresses
  21. L13:1086 weakly excites
  22. L25:2425 weakly suppresses
  23. L14:1038 weakly excites
  24. L15:155 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 -1.55 and -1.471 values between -1.04 and -0.953 values between -0.69 and -0.6110 values between -0.61 and -0.5235 values between -0.52 and -0.4466 values between -0.44 and -0.35202 values between -0.35 and -0.27387 values between -0.27 and -0.18682 values between -0.18 and -0.10914 values between -0.10 and -0.01885 values between -0.01 and 0.08413 values between 0.08 and 0.16166 values between 0.16 and 0.2556 values between 0.25 and 0.3326 values between 0.33 and 0.4215 values between 0.42 and 0.518 values between 0.51 and 0.5913 values between 0.59 and 0.683 values between 0.68 and 0.764 values between 0.76 and 0.852 values between 0.85 and 0.934 values between 0.93 and 1.024 values between 1.02 and 1.104 values between 1.28 and 1.361 values between 1.36 and 1.451 values between 1.53 and 1.622 values between 1.79 and 1.88offnegativepositiveoften

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. 們
  2. င
  3. 물을
  4. ключа
  5. 位
  6. 身
  7. (sys
  8. [position
  9. FormatException
  10. údo

Suppresses

  1. licas
  2. 妇女
  3. cctor
  4. getEmail
  5. 责
  6. ponder
  7. rika
  8. @endforeach
  9. trasound
  10. getKey