Neuron Explorer

Qwen3-0.6B

"the" at the start of a fragment

A neuron in layer 0 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 responds most to the word "the" when it is the very first word of a piece of text, which is often where the sample was cut. The negative side fires on "way" in the phrase "along the way." Steering shows no clear theme.

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

    the Department of Construction, Chaoyang University of Technology, Taichung 4

  2. #2 peak

    the current ISO Guides.⏎- Basic concepts of measurement⏎- Introduction to the topic measurement

  3. #3 peak

    the minute ‘energy factories’ within cells.⏎The mitochondria in the mutant mice don

  4. #4 peak

    the Census then by practically everyone else, themselves included.⏎Census-takers designated them

  5. #5 peak

    the pleural space. As fluid drains into a collection bottle, you may cough a

  6. #6 peak

    the end of the month. Some 40 million people live near their shores,

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 thinking about lately, and I have been thinking about lately, and I have been thinking about lately, and I have been thinking about lately, and I have been thinking about lately, and I have been thinking about lately, and

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

    .⏎The team is also developing new technology along the way. An effective cooling system does not exist for an E-1 class electric vehicle

  2. #2 peak

    as smoking.”⏎Note: We’re about to get science-heavy. You can scroll to the bottom for the takeaways. We’ve also summarized important points along the way.⏎The study itself was part epidemiological and part rodent intervention, and can

  3. #3 peak

    the information by acquiring and practicing these essential auditory skills. The lyrics and music set the stage for listening, learning, and a whole lot of meaningful fun along the way.⏎Take a look at the Read, Sing, Learn: Homophones series

  4. #4 peak

    a disorder characterized by widespread musculoskeletal pain accompanied by fatigue, sleep and mood issues. Researchers believe that fibromyalgia amplifies painful sensations by affecting the way your brain and spinal cord process painful and nonpainful signals.⏎Fibrom

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

None: this is the first layer.

Feeds later layers

  1. L5:493 excites
  2. L10:111 weakly suppresses
  3. L6:1530 weakly suppresses
  4. L20:2469 weakly suppresses
  5. L5:2733 weakly suppresses
  6. L5:420 weakly suppresses
  7. L15:1544 weakly excites
  8. L12:1340 weakly suppresses
  9. L7:566 weakly suppresses
  10. L17:727 weakly suppresses
  11. L9:662 weakly suppresses
  12. L1:206 weakly excites
  13. L23:2975 weakly excites
  14. L3:194 weakly excites
  15. L12:966 weakly excites
  16. L15:1543 weakly suppresses
  17. L10:1232 weakly suppresses
  18. L8:1347 weakly excites
  19. L25:2386 weakly excites
  20. L13:2003 weakly suppresses
  21. L10:1162 weakly excites
  22. L6:1041 weakly suppresses
  23. L13:1234 weakly suppresses
  24. L1:328 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 -1.74 and -1.631 values between -1.51 and -1.403 values between -1.40 and -1.295 values between -1.29 and -1.171 values between -0.95 and -0.832 values between -0.83 and -0.729 values between -0.72 and -0.6014 values between -0.60 and -0.4915 values between -0.49 and -0.3827 values between -0.38 and -0.2647 values between -0.26 and -0.15579 values between -0.15 and -0.042855 values between -0.04 and 0.08279 values between 0.08 and 0.1944 values between 0.19 and 0.319 values between 0.31 and 0.423 values between 0.42 and 0.535 values between 0.53 and 0.653 values between 0.65 and 0.761 values between 0.76 and 0.872 values between 0.87 and 0.991 values between 1.10 and 1.221 values between 1.33 and 1.441 values between 2.69 and 2.81offnegativepositiveoften

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. ovsky
  2. ypass
  3. vag
  4. aget
  5. Gratis
  6. /pkg
  7. Ừ
  8. Gratis
  9. [⏎
  10. �

Suppresses

  1. esting
  2. bàn
  3. Rudd
  4. asty
  5. 练
  6. roperties
  7. Penguins
  8. ocos
  9. 一举
  10. 蜕