Neuron Explorer

Qwen3-0.6B

'by' before a byline or agent

A neuron in layer 9 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 lights up on the word 'by' when it introduces a writer's name, like 'Posted ... by Michael Marsh', or when it introduces who did something. Steering it up made the text repeat itself, so the link to the effect is weak.

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

    code from Marcus Mock exam 2: following code what will be the output?⏎I added UBB code here - Mapraputa [This message has been edited by Mapraputa Is (edited

  2. #2 peak

    .3 light years.⏎The seventh-closest is a star most denizens of Earth would recognise: Sirius (alpha Canis Majoris), with eighth place taken by its companion Sirius B, sometimes referred to as 'the Pup'. Sirius B

  3. #3 peak

    ser is established, and will form again the following year. ®<|endoftext|>Posted: Sep 28, 2009 8:19 PM by Michael Marsh⏎Updated: Sep 28, 2009

  4. #4 peak

    tech gadgets that will protect your home against air pollutants<|endoftext|>Active and Passive Voice – Tips for Content Writing⏎February 22nd, 2012 by Donna Mathews⏎The use of active voice is important while writing online content.

  5. #5 peak

    11:37 am by Matt Prescott<|endoftext|>A significant fraction (~ 30%) of the gamma-ray sources

  6. #6 peak

    affect the performance of the candle in any way and also means your wax<|endoftext|>Equalization - Sound Mixing.⏎May 25, 2004 - by Franck ERNOULDTranslated by Dominique Zbiegiel.⏎In this

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 don't know where I am, but I know that I am not just a tourist. I know that I am not a tourist. I think the most important thing about the time I am being asked to provide information is to 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

    great joy that will be for all the people. 11 For unto you is born this day in the city of David a Savior, who is Christ the Lord.

  2. #2 peak

    municipalities that fall within the district of the court (a geographical area that is included in the district court´s catchment area, usually a number of municipalities).⏎Who do you come into contact with at the district courts?⏎The officers serving at the district

  3. #3 peak

    why it is so significant that the angels described Jesus’ birth as “peace on earth.”⏎9 And an angel of the Lord appeared to them, and the glory of the Lord shone around them, and they were filled with great fear.

  4. #4 peak

    tcp connection is open. Protocol numbers internet assigned numbers authority.⏎Protocol cisco commands ios configuration 61 cheat sheets tagged with network. This number is assigned automatically by the os, manually by the. They are associated with tcpip network connections and

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. L6:1637 strongly excites
  2. L7:194 excites
  3. L6:2756 excites
  4. L8:1494 suppresses preposition right after a passive verb
  5. L6:2937 excites 'by' after a title or author credit
  6. L4:1394 excites
  7. L6:742 excites
  8. L6:1690 excites
  9. L6:408 suppresses
  10. L8:1041 suppresses
  11. L6:3045 excites
  12. L8:351 excites 'in' after 'high' or 'dressed'
  13. L7:360 suppresses
  14. L7:2766 suppresses
  15. L5:2745 suppresses
  16. L6:3070 weakly excites
  17. L8:400 weakly excites
  18. L6:1114 weakly excites
  19. L4:2646 weakly excites
  20. L6:1997 weakly suppresses
  21. L1:2414 weakly suppresses
  22. L5:2890 weakly suppresses
  23. L8:2656 weakly suppresses
  24. L6:716 weakly excites

Feeds later layers

  1. L15:2005 excites
  2. L18:56 excites
  3. L13:2832 excites "by" after a passive verb
  4. L12:1286 excites
  5. L12:2887 excites
  6. L12:755 excites
  7. L13:2465 excites
  8. L12:2535 excites
  9. L13:1291 excites
  10. L17:1221 excites
  11. L10:481 excites word before a noun naming people or a role
  12. L11:3015 excites
  13. L12:2266 excites
  14. L14:2374 excites
  15. L14:1796 excites
  16. L25:343 excites
  17. L25:1291 excites
  18. L11:853 excites
  19. L23:436 excites
  20. L16:2208 excites
  21. L19:2885 excites
  22. L10:362 excites
  23. L22:712 suppresses
  24. L17:505 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.

3 values between -0.83 and -0.711 values between -0.71 and -0.5916 values between -0.59 and -0.4863 values between -0.48 and -0.36264 values between -0.36 and -0.24763 values between -0.24 and -0.131357 values between -0.13 and -0.011014 values between -0.01 and 0.11284 values between 0.11 and 0.2385 values between 0.23 and 0.3419 values between 0.34 and 0.468 values between 0.46 and 0.584 values between 0.58 and 0.695 values between 0.69 and 0.815 values between 0.81 and 0.931 values between 0.93 and 1.042 values between 1.16 and 1.282 values between 1.28 and 1.391 values between 1.39 and 1.512 values between 1.51 and 1.632 values between 1.63 and 1.753 values between 1.86 and 1.981 values between 1.98 and 2.101 values between 2.45 and 2.561 values between 2.91 and 3.031 values between 3.73 and 3.85offnegativepositiveoften

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. 从业者
  2. 队长
  3. etter
  4. emand
  5. Holder
  6. someone
  7. 艺术家
  8. 群体
  9. ainers
  10. professionals

Suppresses

  1. ��
  2. (xi
  3. (nx
  4. 主持召开
  5. Middle
  6. (ti
  7. track
  8. .TryParse
  9. ailles
  10. aim