Neuron Explorer

Qwen3-0.6B

document end token, mixed

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 on the invisible end-of-page marker, but also on some ordinary words in the middle of sentences. The pattern is only partly clear. Turning it up gave repetitive, plain sentences.

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

    velocity (km/s)...?⏎- Inversely proportional⏎- Directly proportional⏎- Linearly related⏎- Non-linearly related⏎Similar Physics resources:<|endoftext|>RNA functions as the central conduit for information transfer in biology - in simple replicating

  2. #2 peak

    viewed by: Khanh-Van Le-Bucklin, Stephanie D'Augustine⏎Last reviewed: May 07, 2008<|endoftext|>As we creep into the peak of hurricane season, many media outlets have dispatched reporters

  3. #3 peak

    , u, t)$.⏎<|endoftext|>While many students view summer as a time to forget about school, it remains an

  4. #4 peak

    Wenjun Chen, Yan Huang, Jiufeng Sun, Jingtao Men, Hailiang Liu, Fang Luo, Lei Guo, Xiaoli Lv<|endoftext|>Laws and Cases: How to Do Legal Research⏎Sometimes you need to look

  5. #5 peak

    round," he said.⏎The results are published in the American Journal of Hypertension.<|endoftext|>Nicolaus Copernicus’ 540th birthday: A man

  6. #6 peak

    y (Zurich).⏎250 pages, 20 x 17 cm, softcover, Edition Patrick Frey (Zurich).<|endoftext|>Pronunciation: (lus'trum), [key]⏎—pl. -

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 number of the phone number. The number of the phone number is the number of the phone number, which is the number of the phone number. The number of the phone number, which is the number of the phone number, which is

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

    Nobel Prize a few years before.⏎"I want to build a steam car which will be practical enough for general use," Howard announced. "I need engineering helpmen who understand the dynamics of steam and can supply them to a workable automobile."⏎Dr

  2. #2 peak

    and some mesotrophic, lakes. Laboratory determination of P release rates from sediment cores is one approach for determining the role of internal P loading and guiding management decisions. Two principal alternatives to experimental determination of sediment P release exist for estimating internal load:

  3. #3 peak

    , show promise. Magnetic devices could be used to move such cells to diseased areas of the body. But current ways of attaching SPIONs to therapeutic cells are difficult to use and may damage the therapeutic cells. So the researchers set out to

  4. #4 peak

    photocathode, often based on NiO, is needed. An important and unknown question is the role of water molecules adsorbed on the NiO surface. Kaijian Zhu performs research on the effects of this adsorption.⏎"In this work

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. L9:1045 suppresses
  2. L8:3040 excites
  3. L7:2652 suppresses
  4. L8:1731 suppresses
  5. L11:1285 excites
  6. L8:2703 excites
  7. L10:981 suppresses
  8. L10:907 suppresses
  9. L8:1937 excites
  10. L4:296 excites
  11. L9:373 suppresses
  12. L9:1815 weakly suppresses
  13. L10:1448 weakly excites
  14. L8:2524 weakly excites
  15. L4:1122 weakly excites
  16. L10:710 weakly suppresses
  17. L7:1112 weakly excites
  18. L11:1482 weakly excites
  19. L10:1577 weakly excites
  20. L10:1579 weakly suppresses
  21. L8:824 weakly suppresses
  22. L10:607 weakly suppresses
  23. L11:3069 weakly excites
  24. L7:563 weakly excites

Feeds later layers

  1. L14:3029 suppresses
  2. L15:1748 suppresses
  3. L15:2327 suppresses
  4. L14:2184 suppresses
  5. L15:506 excites
  6. L13:1338 suppresses
  7. L13:1326 suppresses
  8. L14:2373 suppresses
  9. L13:1396 suppresses
  10. L13:681 suppresses
  11. L14:354 suppresses
  12. L14:410 excites
  13. L14:2284 suppresses
  14. L15:2476 suppresses
  15. L17:2299 suppresses
  16. L15:2047 suppresses
  17. L16:3000 suppresses
  18. L13:2422 weakly suppresses
  19. L14:2186 weakly suppresses
  20. L13:2361 weakly suppresses
  21. L15:1769 weakly suppresses
  22. L14:576 weakly suppresses
  23. L14:654 weakly suppresses
  24. L15:1782 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 -3.30 and -3.171 values between -2.75 and -2.621 values between -2.20 and -2.071 values between -2.07 and -1.931 values between -1.93 and -1.791 values between -1.79 and -1.653 values between -1.65 and -1.522 values between -1.52 and -1.386 values between -1.38 and -1.245 values between -1.24 and -1.106 values between -1.10 and -0.978 values between -0.97 and -0.8315 values between -0.83 and -0.6928 values between -0.69 and -0.5639 values between -0.56 and -0.4272 values between -0.42 and -0.28168 values between -0.28 and -0.14724 values between -0.14 and -0.011618 values between -0.01 and 0.13862 values between 0.13 and 0.27292 values between 0.27 and 0.4143 values between 0.41 and 0.553 values between 0.55 and 0.682 values between 0.68 and 0.821 values between 0.82 and 0.961 values between 0.96 and 1.091 values between 1.09 and 1.231 values between 1.51 and 1.641 values between 1.64 and 1.781 values between 2.06 and 2.19offnegativepositiveoften

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. ירות
  2. EMBER
  3. adget
  4. sgiving
  5. ConfigurationException
  6. ced
  7. 宥
  8. INCIDENTAL
  9. .Factory
  10. افة

Suppresses

  1. oster
  2. ashes
  3. держ
  4. pto
  5. ftar
  6. /res
  7. pps
  8. tems
  9. ��
  10. abs