Neuron Explorer

Qwen3-0.6B

'then' in step-by-step sequences

A neuron in layer 11 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 'then' when a text describes steps in order, such as 'start with X, and then Y'. Turning it up did not produce a clear change in the stories the model wrote.

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

    is a severe type of foodborne illness that causes paralysis by blocking the motor nerve endings; the paralysis progresses downward, usually starting with the eyes and face, and then moving to the throat, chest and extremities<|endoftext|>The Peckham Experiment⏎

  2. #2 peak

    ing design and nozzle selection of musical fountain .⏎For the overall design of the creative fountain, the basic requirements of the environment and atmosphere should be analyzed first, and then the various waterscape forms should be analyzed, different combinations should be listed, and

  3. #3 peak

    take on the world!⏎Talk, Sing and Point⏎Babies learn language from the moment they are born. To a newborn baby, speech is just sound. Then, day by day, they learn that sounds have meaning. Every time you talk

  4. #4 peak

    to our overall health. But if you’re not a person who has always practiced this habit how do you begin? Start with making one healthy choice per meal and then one entire healthy mindful meal per week. More on mindfulness tomorrow.⏎Depending on your

  5. #5 peak

    that doesn't mean you can't teach your 2-year-old to respect others. Begin with the basics (saying "please" and "thank you"), then try these six other strategies.<|endoftext|>This archived Web page remains online for reference,

  6. #6 peak

    » Have a routine. It’s easier to calm down before bed when kids do the same things in the same order. Start with bath time and teeth brushing, then settle in for a bedtime story or section of a chapter book.⏎» Say no

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 writing about the idea that the community is a place where we use language and tools to make sense of our lives and the idea that we use language to make sense of our lives. This is the case every day, but 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

    in a manger.” 13 And suddenly there was with the angel a multitude of the heavenly host praising God and saying,⏎14 “Glory to God in the highest,⏎and on earth peace among those with whom he is pleased!”

  2. #2 peak

    research in the field supporting a link between vocabulary and comprehension.”⏎On a scale of 0-500, fourth-graders scored 224 and eighth-graders scored 2

  3. #3 peak

    movement quantum of light behave as a corpuscular (no charge). b) Using its own inner impulse / intrinsic angular momentum ( h* = h / 2pi ) circle - particle rotates around its axis. In such movement particle has charge,

  4. #4 peak

    as “peace on earth.”⏎9 And an angel of the Lord appeared to them, and the glory of the Lord shone around them, and they were filled with great fear. 10 And the angel said to them, “Fear not

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. L5:540 excites
  2. L4:592 excites
  3. L7:946 weakly suppresses
  4. L6:1652 weakly excites
  5. L9:1667 weakly excites "before" after a do-this-first advice clause
  6. L8:1477 weakly excites
  7. L9:2181 weakly excites
  8. L7:2426 weakly excites
  9. L8:1514 weakly excites 'turn' in 'which in turn'
  10. L9:1477 weakly excites
  11. L9:1748 weakly excites
  12. L9:1780 weakly suppresses
  13. L5:2958 weakly suppresses
  14. L9:1830 weakly suppresses
  15. L9:3018 weakly suppresses
  16. L6:891 weakly excites
  17. L6:2934 weakly suppresses
  18. L7:2896 weakly excites
  19. L0:433 weakly suppresses
  20. L1:2808 weakly suppresses
  21. L5:2380 weakly suppresses
  22. L5:2367 weakly suppresses
  23. L6:2445 weakly suppresses
  24. L2:1846 weakly suppresses

Feeds later layers

  1. L16:2387 excites
  2. L15:961 suppresses
  3. L12:2481 excites
  4. L17:2973 excites
  5. L15:193 suppresses
  6. L16:2591 weakly excites
  7. L14:2375 weakly excites
  8. L13:490 weakly excites
  9. L19:1863 weakly excites
  10. L16:937 weakly excites
  11. L12:1272 weakly excites
  12. L19:1687 weakly excites
  13. L13:1085 weakly excites
  14. L19:3058 weakly excites
  15. L18:1700 weakly excites 'so' in 'and so on'
  16. L17:1318 weakly suppresses
  17. L23:429 weakly excites
  18. L19:2997 weakly excites
  19. L22:2419 weakly excites
  20. L15:456 weakly excites 'and' between two verbs
  21. L16:2949 weakly excites
  22. L13:1724 weakly excites
  23. L13:1435 weakly excites
  24. L19:2349 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.

5 values between -0.75 and -0.53159 values between -0.53 and -0.311102 values between -0.31 and -0.082263 values between -0.08 and 0.14281 values between 0.14 and 0.3635 values between 0.36 and 0.5920 values between 0.59 and 0.8116 values between 0.81 and 1.037 values between 1.03 and 1.254 values between 1.25 and 1.484 values between 1.48 and 1.701 values between 1.70 and 1.922 values between 1.92 and 2.142 values between 2.14 and 2.371 values between 2.37 and 2.591 values between 2.59 and 2.811 values between 2.81 and 3.041 values between 3.04 and 3.261 values between 4.15 and 4.371 values between 5.71 and 5.931 values between 7.93 and 8.16offnegativepositiveoften

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. ucceeded
  2. mieux
  3. urther
  4. [next
  5. athed
  6. .Fl
  7. 埽
  8. ️
  9. .Stage
  10. .Back

Suppresses

  1. คำตอบ
  2. nock
  3. kho
  4. gamle
  5. ogh
  6. ilyn
  7. Vox
  8. cesso
  9. ty
  10. ?><