Neuron Explorer

Qwen3-0.6B

'to' starting an infinitive

A neuron in layer 9 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 'to' in phrases like 'threatens to', 'tend to', or 'is to be', where a verb is about to follow. The opposite side fires on 'to' in phrases like 'want to know' or 'glad to see', so the split is not clean. Turning it up made the text drift and repeat.

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

    applications and it makes me sad. Little curiosities like this can grow into amazing large-scale processes with a bit of support, but a lack of funding threatens to take that away. A public conditioned to a perpetual hype/fatigue cycle are

  2. #2 peak

    aircraft from flying into the sort of engine-seizing ash cast up by Eyjafjallajökull, the low-lying volcano whose plume all but shut down

  3. #3 peak

    we (people) can know objectively and comprehend the objects around us. (146)⏎forms of understanding from which reality is to be deduced. (146)⏎refers to the philosophical movement and

  4. #4 peak

    they have with their family, community, culture and place.⏎Being is about living here and now. Childhood is a special time in life and children need time to just ‘be’- time to play, try new things and have fun.⏎B

  5. #5 peak

    movements needed to do this are controlled by special neuron bundles in the spinal cord. It is not quite clear how these central pattern generators know how quickly the legs are to be moved.⏎An international team working with scientists from Harvard University and the Max Plan

  6. #6 peak

    during illness or with a busy schedule.⏎- ‘Cooking’ up excuses to not eat.⏎- Wears baggy clothes to hide the body.⏎- Going to the bathroom right after meals to throw up the food just eaten.⏎- People with

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 like to have been thinking about think about do something get to go go go go go go go go go go go go go go go go go go go go go go go go go go go go go go go go go go go

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

    also keep them from telling us how they feel.⏎On the other hand, it also isnt wise to confront children with information that they may not yet understand or want to know. As with any sensitive subject, we must seek a delicate balance that encourages

  2. #2 peak

    of that era helped push the reforms that redefined how we live and how much misery we will accept.⏎It was a bargain that most of us would be glad to see return. The problem with today

  3. #3 peak

    were gone."⏎Join to answer this question⏎Join a community of thousands of dedicated teachers and students.Join eNotes<|endoftext|>Is there something else you would like to know?⏎Use the alphabetical glossary listing to find a short definition to a medical

  4. #4 peak

    the state of⏎Andhra Pradesh, it is more comfortable to wear it over a shirt than as a single⏎piece of clothing.⏎Q4. What do you wear on veshti?⏎<|endoftext|>Copyright (c) Arvin S. Quist

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. L6:1880 strongly excites "by" introducing a deadline or means
  2. L6:914 strongly excites
  3. L6:439 suppresses
  4. L6:1133 excites "to" before an infinitive verb
  5. L8:369 suppresses 'of' after 'learned' or 'because'
  6. L6:2747 suppresses
  7. L7:681 excites 'from' after prevent or stop
  8. L4:113 suppresses
  9. L7:751 excites
  10. L6:2359 excites
  11. L8:403 excites
  12. L8:94 excites
  13. L6:751 suppresses
  14. L6:2057 suppresses
  15. L6:2020 excites
  16. L6:2064 suppresses
  17. L4:518 suppresses
  18. L6:1621 suppresses
  19. L1:906 suppresses
  20. L8:1288 suppresses
  21. L8:723 suppresses
  22. L7:1505 suppresses 'the' after a verb or preposition
  23. L7:14 excites
  24. L4:2890 suppresses

Feeds later layers

  1. L16:1153 strongly suppresses
  2. L14:659 strongly suppresses
  3. L17:1592 strongly suppresses
  4. L11:429 strongly suppresses
  5. L19:385 excites
  6. L19:776 suppresses
  7. L18:452 suppresses
  8. L20:480 suppresses
  9. L17:187 suppresses
  10. L24:208 suppresses
  11. L18:141 excites
  12. L19:617 suppresses
  13. L19:876 suppresses
  14. L19:652 suppresses
  15. L18:715 suppresses
  16. L17:1994 suppresses
  17. L16:1291 suppresses
  18. L15:1234 suppresses
  19. L26:1122 suppresses
  20. L18:472 suppresses
  21. L12:434 suppresses
  22. L15:1176 suppresses
  23. L19:1830 suppresses
  24. L20:241 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 -5.16 and -4.981 values between -3.69 and -3.502 values between -3.50 and -3.324 values between -3.32 and -3.141 values between -3.14 and -2.952 values between -2.95 and -2.774 values between -2.58 and -2.405 values between -2.40 and -2.226 values between -2.22 and -2.032 values between -1.85 and -1.668 values between -1.66 and -1.4812 values between -1.48 and -1.299 values between -1.29 and -1.1113 values between -1.11 and -0.9314 values between -0.93 and -0.7442 values between -0.74 and -0.5656 values between -0.56 and -0.3798 values between -0.37 and -0.19639 values between -0.19 and -0.011911 values between -0.01 and 0.18911 values between 0.18 and 0.36136 values between 0.36 and 0.5512 values between 0.55 and 0.734 values between 0.73 and 0.921 values between 0.92 and 1.105 values between 1.10 and 1.282 values between 1.28 and 1.472 values between 1.47 and 1.653 values between 1.84 and 2.022 values between 2.02 and 2.20offnegativepositiveoften

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. precedence
  2. bad
  3. superior
  4. morale
  5. enuity
  6. curacy
  7. sensible
  8. idence
  9. 最佳
  10. ことに

Suppresses

  1. /she
  2. astics
  3. 把她
  4. ски
  5. 把你
  6. rics
  7. unravel
  8. (Android
  9. aska
  10. brities