Neuron Explorer

Qwen3-0.6B

article 'a' after 'here are'

A neuron in layer 3 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 word "a" in the phrase "Here are a few..." and similar list introductions, where a list is about to start. Turning it up made the text drift into unrelated, repetitive wording rather than any clear list.

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

    ocular depth cues aid the detection of moving objects by moving observers.<|endoftext|>Cut flowers need proper care to prolong the length of time you can enjoy them. Here are a few suggestions:⏎- Pick cut flowers in the morning when stems and leaves are t

  2. #2 peak

    SLEEP HYGIENE TIPS:⏎- Create a sleep ritual (a special set of little things) to do before bed to relax the body. Here are a few ideas: stretching, meditation, breathing exercises or gratitude journaling.⏎- Create

  3. #3 peak

    mental health. Here are a few ways giving back can benefit you, just as much as the recipients of your

  4. #4 peak

    good teachers.⏎The above research is supported by a previous study I reported on in, How to Increase Economic Output by $112 Trillion! Here are a couple quotes from that post:⏎Effect of Good Teachers on Students Lifetime Earnings⏎

  5. #5 peak

    harm to our health and wellbeing is clear. You can probably already feel these effects and are looking to find ways to cut down on your screen time. Here are a few simple steps to overcoming the problem of screen time and embracing a digital detox.⏎

  6. #6 peak

    to know what to do to get your middle school child ready for all of the activities, requirements and events that will go on during the school year. Here are a few tips that you can follow that may come in handy as you ready your youngster

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 2000. The numbers 2000. The numbers are. the numbers are. the numbers are. the numbers are. the numbers are. the numbers are. the numbers are. the numbers are

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

    0 with 997 athletes (22 of them women) from 24 countries competing in 95 events. The U

  2. #2 peak

    devastating fire. Smart cities can also help alleviate traffic and address environmental concerns.⏎The Internet of Things (IoT) is a sensor network made up of billions of different smart devices. From small household appliances to large industrial tools, these objects all have

  3. #3 peak

    9 major planets around the sun: Mercury, Venus, the Earth, Mars, Jupiter, Saturn, Uranus, Neptune and Pluto. Only the first five of them (not mentioning the Earth) have been known for thousands of years by many civilizations

  4. #4 peak

    on the U.S. Team in the 1936 Olympic Games held in Berlin, Germany. They won 14 medals — eight of them gold: a quarter of the 56 medals won by the entire U.S

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. L2:149 strongly suppresses
  2. L2:1426 excites
  3. L2:502 excites 'other' after a preposition
  4. L1:683 excites
  5. L2:1120 suppresses
  6. L2:295 weakly excites
  7. L2:1002 weakly excites
  8. L2:2177 weakly suppresses
  9. L0:954 weakly excites
  10. L2:631 weakly suppresses
  11. L1:523 weakly excites
  12. L1:2493 weakly excites
  13. L0:56 weakly excites
  14. L2:326 weakly suppresses
  15. L0:2914 weakly suppresses
  16. L0:69 weakly suppresses
  17. L0:314 weakly suppresses
  18. L2:840 weakly excites
  19. L2:1390 weakly excites
  20. L1:2407 weakly suppresses
  21. L1:1793 weakly excites 'he' in pheasant, 'mouth' in Dartmouth
  22. L1:1691 weakly suppresses
  23. L0:632 weakly excites
  24. L2:1061 weakly suppresses

Feeds later layers

  1. L6:156 strongly excites
  2. L4:450 strongly suppresses
  3. L10:661 strongly excites
  4. L17:2744 strongly excites 'of' after 'those' or 'these'
  5. L7:257 strongly excites
  6. L5:478 strongly excites
  7. L16:1317 strongly excites
  8. L7:146 strongly excites
  9. L10:246 strongly excites
  10. L10:1190 strongly suppresses
  11. L18:1096 strongly excites
  12. L14:1008 strongly excites
  13. L13:535 strongly excites
  14. L9:2445 strongly excites
  15. L11:1684 strongly excites
  16. L4:298 strongly excites
  17. L19:1629 strongly suppresses
  18. L13:1675 strongly suppresses
  19. L6:542 strongly excites
  20. L16:1418 strongly suppresses
  21. L11:2210 strongly excites
  22. L17:1696 strongly excites
  23. L21:275 strongly suppresses
  24. L8:688 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.

2 values between -1.90 and -1.722 values between -1.72 and -1.532 values between -1.53 and -1.356 values between -1.35 and -1.169 values between -1.16 and -0.9812 values between -0.98 and -0.7923 values between -0.79 and -0.6160 values between -0.61 and -0.42194 values between -0.42 and -0.24991 values between -0.24 and -0.052282 values between -0.05 and 0.13242 values between 0.13 and 0.3251 values between 0.32 and 0.5013 values between 0.50 and 0.686 values between 0.68 and 0.878 values between 0.87 and 1.051 values between 1.05 and 1.241 values between 1.42 and 1.611 values between 1.98 and 2.161 values between 2.16 and 2.351 values between 5.30 and 5.48offnegativepositiveoften

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. 各自的
  2. 各自
  3. 也都
  4. elves
  5. którzy
  6. paces
  7. köp
  8. aren
  9. èrent
  10. _are

Suppresses

  1. itself
  2. Its
  3. Its
  4. its
  5. vention
  6. iene
  7. halfway
  8. uario
  9. 率达
  10. behind