Neuron Explorer

Qwen3-0.6B

unclear: personal names, mostly Indian

A neuron in layer 4 of Qwen3-0.6B. Its strongest snippets are fairly consistent: several of them peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron tends to fire on parts of people's names, especially Indian and Hindu names such as Ram, Surendra and Shyam. The pattern is not very strong, and the steering results do not show 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

    etc. There is no confusion in the first name. The middle name can be seen from example – Ram Prasad Srivastava. Here First Name is Ram, Middle name is Prasad and Last name is Srivastava.⏎What

  2. #2 peak

    he toured South India extensively and composed songs on the various deities of the religious pantheon. He had met both Tyāgarāja and Śyām<|endoftext|>Different cultures have been using psychedelic substances in rituals for thousands of years. In

  3. #3 peak

    18).⏎Air Transport Law: Air transport law legislation aims safety of air passengers and implements rules regarding carriage. And also, ensures the passengers' rights to redressal for personal injury or damage.⏎2.1<|endoftext|>Vitamin D has at

  4. #4 peak

    of freedom and it is freed from the clutches of British rule. During the partition of Bengal and freedom by the indigenous movement in which Sir Henry Cotton Surendra Nath Banerjee and turned into a

  5. #5 peak

    birth, deciding its:⏎- ↑ Yogasutras 2.73⏎- The Concise Encyclopedia of Hinduism, Swami Harshananda, Ram Krishna Math, Bangalore<|endoftext|>Lancashire food producers and farmers have been working with

  6. #6 peak

    with Kasturba makanji. After that, he went to London to complete his bar studies. Later he worked at Indian firm in South Africa. While living in South Africa protest a war against racism in South Africa.⏎In 1

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 problem is a triangle with the given side. The problem is a triangle with the given side. The triangle is formed by the two sides. The triangle is formed by the given side. The triangle is formed by the given side. 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

    all are waiting for. Teachers, parents and student, now you will find below the Solutions of Class 10 Science Chapter 4 Environmental management questions answers. From the subject English of Maharashtra State Board.⏎Below you can see

  2. #2 peak

    class 10 appearing for the board exams. Students can easily NCERT Solutions for Class 10 Maths Exercise 6.5 Chapter 6 Triangles from below.⏎CBSE Class 10 Maths Chapter 6 Triangles Exercise

  3. #3 peak

    ⏎(iv) For series RLC circuit at resonance, the phase angle is zero and cos . ϕ =1⏎∴ Pav = VRMS IRMS⏎Consider an AC circuit in which there is a phase angle of ϕ between VRMS

  4. #4 peak

    2012 June 23⏎Explanation: As seen from Frösön island in northern Sweden the Sun did set a day after the summer

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. L3:62 excites
  2. L3:318 suppresses
  3. L3:249 excites
  4. L3:615 suppresses
  5. L3:506 weakly suppresses
  6. L3:153 weakly suppresses
  7. L1:2908 weakly suppresses
  8. L3:691 weakly excites
  9. L0:1768 weakly suppresses
  10. L3:421 weakly suppresses
  11. L3:530 weakly suppresses
  12. L3:2369 weakly suppresses
  13. L1:2278 weakly excites
  14. L2:1578 weakly excites
  15. L3:1907 weakly excites
  16. L3:189 weakly excites
  17. L2:2010 weakly suppresses
  18. L0:1515 weakly suppresses
  19. L2:2282 weakly excites
  20. L1:2677 weakly suppresses
  21. L1:2502 weakly suppresses
  22. L1:3007 weakly excites
  23. L3:880 weakly suppresses
  24. L0:1539 weakly suppresses

Feeds later layers

  1. L8:369 weakly suppresses 'of' after 'learned' or 'because'
  2. L5:2705 weakly excites
  3. L8:423 weakly excites
  4. L5:667 weakly excites
  5. L10:2186 weakly suppresses
  6. L25:2901 weakly suppresses
  7. L14:1515 weakly suppresses
  8. L19:967 weakly excites
  9. L10:2752 weakly excites
  10. L5:2599 weakly excites
  11. L6:1695 weakly excites
  12. L15:1280 weakly excites
  13. L27:2138 weakly suppresses
  14. L25:2623 weakly suppresses
  15. L5:418 weakly excites
  16. L9:1621 weakly suppresses
  17. L18:2238 weakly excites
  18. L14:659 weakly excites
  19. L12:2087 weakly suppresses
  20. L5:2799 weakly suppresses
  21. L9:1434 weakly suppresses
  22. L16:2448 weakly suppresses
  23. L25:2213 weakly suppresses
  24. L17:552 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 -2.47 and -2.381 values between -1.43 and -1.333 values between -1.05 and -0.951 values between -0.77 and -0.673 values between -0.67 and -0.584 values between -0.58 and -0.489 values between -0.48 and -0.3940 values between -0.39 and -0.29107 values between -0.29 and -0.20343 values between -0.20 and -0.10982 values between -0.10 and -0.011451 values between -0.01 and 0.09679 values between 0.09 and 0.18211 values between 0.18 and 0.2849 values between 0.28 and 0.374 values between 0.37 and 0.4711 values between 0.47 and 0.561 values between 0.56 and 0.663 values between 0.66 and 0.751 values between 0.75 and 0.852 values between 0.85 and 0.941 values between 1.04 and 1.131 values between 1.23 and 1.32offnegativepositiveoften

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. 免
  2. mailto
  3. .setInput
  4. 就不
  5. ows
  6. feld
  7. ós
  8. 将其
  9. -Time
  10. act

Suppresses

  1. 道路上
  2. earer
  3. 瞎
  4. anthology
  5. ighest
  6. icked
  7. abyrin
  8. меща
  9. .localization
  10. UNDLE