Neuron Explorer

Qwen3-0.6B

'be' after 'to' in infinitives

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 responds to the word 'be' when it comes after 'to' or 'designed to', as in 'not meant to be taken' or 'suitable to be read'. Turning it up or down did not clearly change the topic of what 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

    appellation of his is known in China, Târanâtha mentions nine more names: Kâla (Time), Durdarsha (Hard-to-be-seen), Durdarshakâla (Hard-to-be-seen

  2. #2 peak

    treat spinal curvature, including scoliosis and kyphosis, in our patients at Woodbury Spine.⏎Adult spinal curvature⏎Your spine is not designed to be completely straight. It has subtle front-to-back curves to help provide support and movement

  3. #3 peak

    and hotels. They hide nearly everywhere and spread easily from one place to another in backpacks, suitcases, linens, shoes, clothes, and boxes to be near a food source.⏎After feeding, they move to secluded places and hide for

  4. #4 peak

    “St. Valentines,” each clamoring to be recognized as the day’s patron saint, but here’s the most romantic story:⏎

  5. #5 peak

    their way. If you cheat, your transaction does not get forwarded.⏎I hope that explains the concept of how Bitcoin works in regards to your question. Just to be clear:⏎"Does each bitcoin has a unique identifier,

  6. #6 peak

    Add your thoughts below. You can sign in with Google, Twitter, Facebook, Yahoo! to get your story posted straight away - or just post a comment to be published later.⏎Let us help you plan a route and make a visit<|endoftext|>Pre

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 question is: This is a question that is still: This is a question that is not. I think that's the answer. So, in the case of the question is: The answer is. So, in the case of 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

    Enterprise, were mobilized to respond to a distress call from Vulcan, which was under attack by the Narada. After the destruction of Vulcan, acting captain Spock planned to regroup with the rest of the fleet in the Laurentian system to

  2. #2 peak

    rampant poaching that takes advantage of the “arribadas” (arrival of nesting sea turtles

  3. #3 peak

    ley nests each year.⏎WildAid completed an enforcement assessment last year of three marine protected areas (MPAs) in Nicaragua’s coral corridor to address turtle poaching and other threats to the region’s biodiversity. Sea turtle eggs are considered delicacies

  4. #4 peak

    Deacons are also supposed to have a demonstrated ability to manage their households well. This may suggest they had certain administrative functions within the church.[i]⏎There may have been other areas entrusted to deacon as well. The term deacon, after

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. L0:1183 weakly suppresses
  2. L0:1 weakly suppresses
  3. L2:1036 weakly excites
  4. L1:2340 weakly suppresses
  5. L2:2940 weakly excites
  6. L0:1224 weakly suppresses
  7. L2:483 weakly suppresses
  8. L0:1675 weakly suppresses
  9. L2:2930 weakly suppresses
  10. L1:92 weakly excites
  11. L0:1247 weakly suppresses
  12. L0:178 weakly suppresses
  13. L1:1742 weakly excites
  14. L1:1363 weakly excites
  15. L0:2522 weakly excites
  16. L0:1301 weakly suppresses
  17. L0:1256 weakly suppresses
  18. L2:1343 weakly suppresses
  19. L2:1121 weakly suppresses "for" after "hard" or "difficult"
  20. L2:1899 weakly excites
  21. L0:294 weakly suppresses
  22. L2:1657 weakly excites
  23. L0:2007 weakly suppresses 'key' after 'The'
  24. L2:1184 weakly excites

Feeds later layers

  1. L16:1096 weakly suppresses
  2. L19:2934 weakly suppresses
  3. L15:284 weakly suppresses
  4. L7:2777 weakly suppresses
  5. L11:2471 weakly excites commas in lists of six items
  6. L18:1749 weakly excites
  7. L16:879 weakly suppresses
  8. L6:1932 weakly suppresses
  9. L8:529 weakly excites
  10. L24:2893 weakly suppresses
  11. L8:2296 weakly excites
  12. L14:2770 weakly suppresses
  13. L18:1779 weakly suppresses
  14. L9:1027 weakly excites 'to' or 'on' after 'was' or 'were' (planned future action)
  15. L22:758 weakly excites
  16. L9:2242 weakly suppresses
  17. L7:2647 weakly suppresses
  18. L17:2307 weakly excites
  19. L4:3018 weakly excites
  20. L18:1955 weakly suppresses
  21. L25:3067 weakly excites
  22. L10:2446 weakly suppresses
  23. L4:2553 weakly suppresses
  24. L25:565 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.

1 values between -1.01 and -0.782 values between -0.78 and -0.5633 values between -0.56 and -0.34875 values between -0.34 and -0.122606 values between -0.12 and 0.11358 values between 0.11 and 0.3316 values between 0.33 and 0.551 values between 0.55 and 0.783 values between 0.78 and 1.001 values between 1.22 and 1.441 values between 1.44 and 1.672 values between 1.67 and 1.891 values between 2.33 and 2.561 values between 2.56 and 2.781 values between 3.00 and 3.221 values between 3.22 and 3.451 values between 3.89 and 4.111 values between 4.11 and 4.341 values between 6.34 and 6.561 values between 6.56 and 6.781 values between 7.67 and 7.90offnegativepositiveoften

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. shake
  2. hawk
  3. pie
  4. amen
  5. auty
  6. trade
  7. uar
  8. shares
  9. maid
  10. pher

Suppresses

  1. �能
  2. quires
  3. iveness
  4. erno
  5. ọi
  6. 您的
  7. ively
  8. Reconstruction
  9. 辙
  10. 万名