Neuron Explorer

Qwen3-0.6B

'see' cross-references and web boilerplate

A neuron in layer 16 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 fires in website and reference text, mostly on words that point you somewhere else, like 'See' in 'See RAID 0', 'See more articles on', or 'click anywhere to close'. Turning it up made the model write in a more general, listy style, with no obvious link to the trigger.

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

    showing you is much cooler than explaining it.⏎Thanks for Subscribing!⏎You'll need to confirm your email, so please check your inbox.⏎(click anywhere to close)<|endoftext|>According to findings of a major HIV prevention trial presented Monday, March

  2. #2 peak

    © 2012, Columbia University Press. All rights reserved.⏎More on rheology from Fact Monster:⏎See more Encyclopedia articles on: Physics<|endoftext|>A startling statement is found in Mark 9:48. In

  3. #3 peak

    www.msfc.nasa.gov/news⏎The above story is based on materials provided by NASA's Marshall Space Flight Center. Note: Materials may be edited for content and length.⏎Cite This Page:<|endoftext|>By A. M. Sullivan⏎CHAPTER IX

  4. #4 peak

    consider the Requirements for RAID 5 Volumes and Guidelines for RAID 5 Volumes. Many striping guidelines also apply to RAID 5 volume configurations. See RAID 0 Volume Requirements.⏎A RAID 5 volume

  5. #5 peak

    the lower case letter L (for 'length'). For eaxmaple⏎would be read as "the length of the arc AB is 6 inches". See Arc Length page for more.⏎The angle measure is the angle formed by the arc at

  6. #6 peak

    to another dc voltage.⏎Current — See electric current.⏎DC — See<|endoftext|>Cherry Creek History⏎The Cherry Creek region is one of Nevada's oldest

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 like that, but you can't say that, or that; or that; or that; and so on; and so on; and so on. and so on; and so on; and so on; and so on.

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

    pneumonia. However, those living in the sunnier communities had lower death rates after developing influenza than those living in the less sunny communities. Vitamin D helped in two ways: first by reducing the aggressive immune response that among other things ruptured some of

  2. #2 peak

    bacteria that lead to pneumonia.⏎There is also good evidence that vitamin D reduces the risk of viral infections. Influenza is more common in winter for two reasons: cold temperatures and low solar UVB doses and vitamin D production. A randomized

  3. #3 peak

    the WHO Report on Global Tobacco Epidemic 2008 has recommended a six-point policy package called MPOWER for effective tobacco control. These policies are: (i) Monitor tobacco use and prevention policies (Article 20); (ii

  4. #4 peak

    This is likely due to a combination of factors, including Tesla’s higher battery capacity.⏎“There are several potential explanations for why EV

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. L15:717 excites
  2. L14:667 suppresses
  3. L15:2871 suppresses
  4. L15:512 excites
  5. L15:3019 excites
  6. L15:427 suppresses
  7. L15:2610 excites
  8. L13:52 suppresses
  9. L15:1990 suppresses
  10. L15:917 suppresses
  11. L14:1333 suppresses
  12. L15:1119 excites
  13. L14:702 suppresses
  14. L15:746 excites
  15. L15:506 excites
  16. L15:2258 suppresses
  17. L10:2423 suppresses
  18. L15:551 suppresses
  19. L15:645 excites
  20. L13:19 suppresses
  21. L15:774 excites
  22. L13:3032 excites
  23. L12:207 suppresses
  24. L14:1939 suppresses

Feeds later layers

  1. L17:1088 strongly excites
  2. L18:1171 excites
  3. L17:933 excites
  4. L17:2648 excites number word before a list of reasons
  5. L17:2384 excites
  6. L17:1430 excites
  7. L18:1636 suppresses
  8. L20:631 excites
  9. L17:1718 excites
  10. L17:1267 excites
  11. L18:2151 excites
  12. L22:2193 excites
  13. L17:1930 excites
  14. L19:2057 suppresses
  15. L18:2837 excites
  16. L17:450 suppresses
  17. L18:1948 excites
  18. L18:1031 excites
  19. L18:2722 suppresses
  20. L19:2776 excites
  21. L22:1428 excites
  22. L21:1049 weakly excites
  23. L20:460 weakly excites
  24. L19:657 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.

2 values between -1.89 and -1.704 values between -1.70 and -1.513 values between -1.51 and -1.3217 values between -1.32 and -1.1324 values between -1.13 and -0.9434 values between -0.94 and -0.7489 values between -0.74 and -0.55162 values between -0.55 and -0.36270 values between -0.36 and -0.17858 values between -0.17 and 0.02745 values between 0.02 and 0.21512 values between 0.21 and 0.41313 values between 0.41 and 0.60240 values between 0.60 and 0.79182 values between 0.79 and 0.98130 values between 0.98 and 1.1786 values between 1.17 and 1.3674 values between 1.36 and 1.5542 values between 1.55 and 1.7538 values between 1.75 and 1.9427 values between 1.94 and 2.1321 values between 2.13 and 2.329 values between 2.32 and 2.515 values between 2.51 and 2.707 values between 2.70 and 2.892 values between 2.89 and 3.092 values between 3.09 and 3.283 values between 3.28 and 3.472 values between 3.66 and 3.851 values between 3.85 and 4.041 values between 4.04 and 4.232 values between 4.62 and 4.811 values between 5.57 and 5.77offnegativepositiveoften

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. ':⏎⏎
  2. fix
  3. ---⏎⏎
  4. 面前
  5. 什么呢
  6. exels
  7. przec
  8. 是什么呢
  9. ###
  10. ":⏎⏎

Suppresses

  1. <|endoftext|>
  2. otropic
  3. jure
  4. ouv
  5. ⏎ ⏎ ⏎
  6. acades
  7. vertising
  8. goog
  9. tré
  10. awns