Neuron Explorer

Qwen3-0.6B

unclear: mid-sentence function words

A neuron in layer 20 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 is hard to pin down. It lights up on small connecting words and full stops in ordinary sentences, often right before the next phrase starts. When it was turned up, the model got stuck repeating a few words.

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

    and distributed to classrooms all over the world. They also offer workshops to assist K-12 teachers interested in integrating bioenergy into their curricula. In addition, a bioenergy literacy search tool is available to help education professionals find

  2. #2 peak

    that your data is backed up and accessible even if one data centre experiences an outage or disruption. Regular data backups protect against data loss and provide continuity for your business.⏎Cloud providers have dedicated teams of security experts who continually monitor and update security protocols.

  3. #3 peak

    physics professor Wilhelm Röntgen who discovered the use of an X-Ray way back in 1895.⏎Google doesn’t forget anyone though, and to celebrate, visiting their homepage will bring up a cool blue neon design. You may

  4. #4 peak

    so famous that it has been used as the title of books, movies, and albums.⏎It has also been used to describe periods of history.⏎The reason for this line’s popularity is quite understandable – many people have experienced a season of discontent.⏎

  5. #5 peak

    his own queen and provided her with a pension instead. A year earlier she had taken out a lease on the mansion of Cheynegates in Westminster Abbey but by 1492 she was resident at Bermondsey Abbey where she made

  6. #6 peak

    2.054 of the Texas Property Code governs judicial<|endoftext|>Adjustment to college life after school is always a challenge for young adults. One reason to be unsuccessful in navigating stress, depression, anxiety during college days is that the maturity and

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 following is a well-known example of a well- for which the following is so well-known, and so it can be generalized, but I can't for that, so it is on the following I am with that, and so I

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

    earnings.⏎Preferred stock, or preference shares.⏎To appeal to investors who wish to be sure of receiving dividends regularly, many companies issue what is called preferred stock, or preference shares. This class of stock has a prior claim to dividends paid by the

  2. #2 peak

    situation.⏎Sometimes you might want to return objects of different types based on arguments to the function. For instance, did the caller ask for the data in this format or that format?⏎Sometimes you'll want all of these variations at the same time.

  3. #3 peak

    like that (although, of course, the weights don't weigh anything) by creating a virtual reality simulator called the Cave Automatic Virtual Environment, or just CAVE, that works by tracking your muscle movements. Users put on a pair of goggles and

  4. #4 peak

    from Greenwich, England. Because of this strategic position, the humble outcrop of coral and sand became an important point in the journey by sea and later, air, between the US and Asia. The first attempt to establish Midway as a strategic

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. L19:2215 excites
  2. L19:1516 excites
  3. L18:569 suppresses
  4. L19:223 suppresses
  5. L14:177 excites
  6. L19:1875 excites
  7. L19:2793 suppresses
  8. L19:413 suppresses
  9. L19:535 excites
  10. L19:1713 excites
  11. L18:1479 suppresses
  12. L9:11 excites
  13. L19:1554 excites
  14. L19:2037 excites
  15. L19:1659 suppresses
  16. L16:2531 suppresses
  17. L18:93 suppresses
  18. L17:336 suppresses
  19. L14:67 excites
  20. L11:29 suppresses
  21. L19:1662 excites
  22. L18:116 suppresses
  23. L19:840 excites
  24. L13:81 weakly excites

Feeds later layers

  1. L27:239 strongly excites
  2. L24:563 strongly suppresses
  3. L27:467 strongly suppresses
  4. L25:477 suppresses
  5. L21:720 suppresses
  6. L26:187 excites
  7. L23:100 suppresses comma or full stop ending a clause
  8. L21:102 excites
  9. L23:598 excites
  10. L26:836 suppresses
  11. L27:1300 excites
  12. L21:177 suppresses
  13. L26:11 suppresses
  14. L27:775 suppresses
  15. L21:717 excites
  16. L26:993 excites
  17. L23:235 suppresses
  18. L25:452 suppresses
  19. L25:469 suppresses
  20. L25:334 suppresses
  21. L21:930 suppresses
  22. L21:344 excites
  23. L26:255 excites
  24. L27:575 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 -15.06 and -14.271 values between -13.48 and -12.701 values between -12.70 and -11.911 values between -11.91 and -11.126 values between -11.12 and -10.338 values between -10.33 and -9.5410 values between -9.54 and -8.7520 values between -8.75 and -7.9615 values between -7.96 and -7.1726 values between -7.17 and -6.3847 values between -6.38 and -5.5955 values between -5.59 and -4.81102 values between -4.81 and -4.02105 values between -4.02 and -3.23163 values between -3.23 and -2.44240 values between -2.44 and -1.65346 values between -1.65 and -0.86443 values between -0.86 and -0.07575 values between -0.07 and 0.72398 values between 0.72 and 1.51345 values between 1.51 and 2.30235 values between 2.30 and 3.09199 values between 3.09 and 3.88140 values between 3.88 and 4.66106 values between 4.66 and 5.45103 values between 5.45 and 6.2457 values between 6.24 and 7.0334 values between 7.03 and 7.8233 values between 7.82 and 8.6131 values between 8.61 and 9.4025 values between 9.40 and 10.1914 values between 10.19 and 10.988 values between 10.98 and 11.777 values between 11.77 and 12.562 values between 12.56 and 13.344 values between 13.34 and 14.131 values between 14.13 and 14.921 values between 15.71 and 16.50offnegativepositiveoften

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. .");
  3. .";
  4. .",
  5. ."));⏎
  6. )。
  7. .");⏎
  8. %).
  9. .');
  10. ?",

Suppresses

  1. )
  2. \)
  3. ()
  4. )
  5. ')'
  6. }
  7. ]
  8. ()
  9. ""
  10. ''