Neuron Explorer

Qwen3-0.6B

words inside idioms and fixed phrases

A neuron in layer 11 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron tends to light up on the word inside a set phrase, such as 'round' in 'centred round', 'about' in 'roundabout way', 'order' in 'in order to' or 'matter' in 'a matter of course'. It is weakest on words like 'focus' or 'name' that come right after 'the' or 'to' in a sentence. Turning it up or down did not give a 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

    , equipped with smoke lifters ("wind wings" in UP parlance), and painted two-tone gray in 1946.⏎It was in a roundabout way that six Challengers ordered by the UP ended up hauling coal for the Clin

  2. #2 peak

    or a curse. Border Collies, for instance, can be easily trained due to their high intelligence. If one decides to resist training, however, he can run circles around you — mentally and physically.⏎It may sound insulting to claim a dog

  3. #3 peak

    skills with this cool easter egg activity. You get to re-use your plastic eggs and recycle your egg cartons with one awesome easter craft. I pinky promise this activity is quick and easy.⏎We had so much fun making our own

  4. #4 peak

    be converted by the action of heat or electricity. Again, on account of the great value of the diamond, much of the romance of precious stones has centred round this mineral; and the history of some of the great diamonds of historic times has

  5. #5 peak

    as coconut milk yogurt, can be substituted⏎• 12-14 ounces (more if you like

  6. #6 peak

    that are more dangerous than machine guns.<|endoftext|>There are several options to explore. Choose one, research it and write about your findings on your blog.⏎This kindling of engagement

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 am a teacher and I have to do this in the middle of the night. I am a teacher and I am trying to make a child learn, and I am trying to make the world go around, so I am trying to

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

    about this formula and background on the material properties in Planck, Stefan-Boltzmann, Kirchhoff and LTE.⏎The parameter called emissivity is the focus of this article. It is of special interest because to calculate the radiation from the

  2. #2 peak

    such as the ways enslaved peoples fought for liberation, workers’ rights movements, the intimate relationships of families, and the power struggles of monarchs and presidents, to name only a few.⏎History faculty are committed to fostering a classroom environment which is welcoming

  3. #3 peak

    adjacent nodes (not including the node itself). Our depiction of graphs will look much like our depiction of trees. This should come as no surprise because, if you recall, trees are a special case of graphs.⏎

  4. #4 peak

    Note that the incised lines on the bird-form piece⏎are very much⏎like those on the Venus figure.<|endoftext|>Think Eat Save⏎Here’s some food for thought: Are you aware that a lot of food waste comes from our homes?

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. L9:200 strongly suppresses
  2. L6:237 strongly excites
  3. L9:591 strongly excites
  4. L9:211 excites
  5. L10:452 suppresses
  6. L10:621 suppresses
  7. L9:1 suppresses
  8. L9:346 suppresses
  9. L10:251 suppresses
  10. L8:281 excites
  11. L5:12 suppresses
  12. L10:2389 suppresses
  13. L9:326 suppresses
  14. L6:561 excites
  15. L4:2 suppresses
  16. L2:553 suppresses
  17. L10:707 excites
  18. L8:60 excites
  19. L5:214 suppresses
  20. L10:346 suppresses "each" in "each other" phrases
  21. L6:124 suppresses
  22. L9:799 excites
  23. L8:733 suppresses "of" after a noun phrase
  24. L6:2371 excites

Feeds later layers

  1. L15:1662 strongly excites
  2. L14:1394 strongly excites
  3. L15:1186 strongly excites
  4. L16:1059 strongly excites
  5. L17:1323 strongly excites
  6. L13:1470 excites
  7. L14:1925 excites
  8. L12:707 excites
  9. L13:793 excites
  10. L14:1411 excites
  11. L17:1171 excites
  12. L16:2942 excites
  13. L12:1978 excites
  14. L18:1483 excites
  15. L20:804 excites
  16. L13:2505 excites
  17. L16:1019 excites
  18. L13:495 excites
  19. L15:2777 excites
  20. L14:1304 excites
  21. L17:1783 excites
  22. L12:1833 excites
  23. L13:683 excites
  24. L15:431 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 -5.21 and -5.021 values between -3.10 and -2.912 values between -2.72 and -2.523 values between -2.52 and -2.337 values between -2.14 and -1.953 values between -1.95 and -1.763 values between -1.76 and -1.565 values between -1.56 and -1.3710 values between -1.37 and -1.1821 values between -1.18 and -0.9918 values between -0.99 and -0.8053 values between -0.80 and -0.60254 values between -0.60 and -0.41765 values between -0.41 and -0.221230 values between -0.22 and -0.031202 values between -0.03 and 0.16179 values between 0.16 and 0.3672 values between 0.36 and 0.5529 values between 0.55 and 0.7416 values between 0.74 and 0.9317 values between 0.93 and 1.126 values between 1.12 and 1.324 values between 1.32 and 1.513 values between 1.51 and 1.702 values between 1.70 and 1.891 values between 1.89 and 2.081 values between 2.28 and 2.47offnegativepositiveoften

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. необходимости
  2. 因为他们
  3. EqualTo
  4. Their
  5. besoin
  6. 注意到
  7. 的印象
  8. 说明
  9. their
  10. 让他们

Suppresses

  1. da
  2. acea
  3. tắt
  4. autour
  5. GRESS
  6. -native
  7. thic
  8. sei
  9. زن
  10. 处