Neuron Explorer

Qwen3-0.6B

document end markers and disc brakes

A neuron in layer 7 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 is mixed. It fires most on the hidden 'end of document' marker that web pages use between unrelated texts, and also on the phrase 'disc brakes'. Its negative side is weak and hard to read. Turning it up or down did not produce a clear theme in the model's writing.

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

    Nov 23, 2021, 1 PM⏎World StampsNov 22, 2021, 7 PM<|endoftext|>At SACRE, the Fluent CFD code has been used in the past

  2. #2 peak

    please your palate for centuries to come.⏎KONISHI BREWING CO., LTD.⏎3-5-8, Chuo, Itami city,<|endoftext|>Materials

  3. #3 peak

    , Light and Space of the Medieval Cathedrals of England and France" in 1973 (Aperture).⏎|[Checklist]||Click<|endoftext|>The unmanned Jules Verne ATV cargo ship breaks up in a spectacular display⏎

  4. #4 peak

    as are the essence of Mexican food⏎- What Is the Difference Between Fruits and Vegetables?⏎Try Our Delicious Dishes!⏎Contact us today by telephone (<|endoftext|>One food which dates back in prehistoric times is the date. Here is truly

  5. #5 peak

    782-7937)⏎For more information on activities ongoing within EPA Region 7 (Iowa, Kansas, Missouri and Nebraska), contact:<|endoftext|>According to the analysis of the cutting process oftooth surface, based on the

  6. #6 peak

    ," he said.<|endoftext|>Disc Brake Rotor Specsby Craig Woodman⏎Four-wheel disc brakes have become more common in vehicles because of their increased stopping power. Disc brakes are a reliable system, but still need routine maintenance. In addition to replacing

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 never been aware that the car is equipped with a certain model of gear shift, the car is equipped with a certain model of foot, or the car is equipped with a certain model of wheel to the left or right position for 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

    a review, the scientific knowledge about fitness for transport is reviewed against the background of the relevant European legislation.⏎Injury and unnecessary suffering⏎The European regulation (Council Regulation 1/2005 and to a lesser extent 853

  2. #2 peak

    by By Dr. Carolyn K. Stratz⏎Q: My kids get their vaccinations - what about me?⏎A: Back-to-school time

  3. #3 peak

    - Quiz Questions & Answers⏎- Which Italian inventor succeeded in transmitting wireless waves over long distances for the first time?⏎-

  4. #4 peak

    long does it take for vision therapy to work?⏎Most children begin actually noticing a difference within six to eight weeks, about midway through the typical therapy program. Q: Will my child’s vision problem come back later in life? A: Generally speaking

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. L6:1825 suppresses
  2. L3:105 weakly suppresses
  3. L5:1498 weakly suppresses
  4. L5:78 weakly suppresses
  5. L5:458 weakly excites
  6. L5:741 weakly excites
  7. L4:1542 weakly suppresses
  8. L3:894 weakly suppresses
  9. L3:3049 weakly excites
  10. L4:2510 weakly suppresses
  11. L2:570 weakly suppresses
  12. L5:1391 weakly suppresses
  13. L2:1965 weakly suppresses
  14. L6:1083 weakly suppresses
  15. L1:2726 weakly suppresses
  16. L2:2602 weakly suppresses
  17. L4:1051 weakly suppresses
  18. L6:892 weakly suppresses
  19. L1:1728 weakly suppresses
  20. L5:198 weakly excites unclear: weak "and" in lists
  21. L4:1691 weakly excites
  22. L5:1636 weakly suppresses
  23. L3:237 weakly excites
  24. L3:898 weakly suppresses

Feeds later layers

  1. L8:950 excites
  2. L20:1413 suppresses
  3. L9:498 weakly excites
  4. L9:2341 weakly suppresses
  5. L19:846 weakly excites
  6. L10:291 weakly excites
  7. L9:720 weakly suppresses
  8. L18:1990 weakly suppresses
  9. L27:1203 weakly excites
  10. L9:33 weakly suppresses
  11. L12:1840 weakly excites
  12. L22:312 weakly suppresses
  13. L17:2136 weakly suppresses
  14. L9:128 weakly excites
  15. L17:1881 weakly suppresses
  16. L14:1839 weakly suppresses
  17. L17:1629 weakly suppresses
  18. L21:429 weakly suppresses
  19. L14:2556 weakly suppresses
  20. L24:2543 weakly suppresses
  21. L18:2610 weakly suppresses
  22. L14:650 weakly excites
  23. L15:552 weakly excites
  24. L12:1804 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.

2 values between -1.47 and -1.341 values between -1.34 and -1.221 values between -1.22 and -1.102 values between -1.10 and -0.972 values between -0.97 and -0.853 values between -0.85 and -0.737 values between -0.73 and -0.6010 values between -0.60 and -0.4834 values between -0.48 and -0.3696 values between -0.36 and -0.23443 values between -0.23 and -0.111605 values between -0.11 and 0.011156 values between 0.01 and 0.14383 values between 0.14 and 0.26103 values between 0.26 and 0.3829 values between 0.38 and 0.5114 values between 0.51 and 0.635 values between 0.63 and 0.753 values between 0.75 and 0.883 values between 0.88 and 1.001 values between 1.00 and 1.122 values between 1.12 and 1.241 values between 1.37 and 1.491 values between 1.74 and 1.861 values between 3.34 and 3.46offnegativepositiveoften

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. ())[
  2. grav
  3. ��이
  4. )[-
  5. 랩
  6. знания
  7. ()};⏎
  8. ());⏎⏎⏎
  9. ();⏎⏎⏎
  10. ");⏎⏎⏎

Suppresses

  1. بارك
  2. 嚏
  3. roys
  4. moot
  5. aż
  6. /history
  7. oyal
  8. 茬
  9. licensors
  10. :UIAlert