Neuron Explorer

Qwen3-0.6B

'with' after a verb of action

A neuron in layer 6 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 reacts to the word 'with' when it comes right after an action verb, as in 'covered it with' or 'responded to ... with'. Turning it up did not produce a clear change in the model's replies.

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

    deck (it can be the teacher, or the players can take turns picking a card), and if a player has that picture on their board, they cover it with a penny or a dried bean. The winner is the

  2. #2 peak

    Antwerp, the Belgian athlete Omar Smet, who was a member of the KAA Gent athletic department, responded to the rhythmical cheering of the American delegation with the student yell ‘Buffalo! Buffalo!’ Together with him, KAA Gent

  3. #3 peak

    arguing that the Brazilian Constitution defines a "family entity" as "a stable union between a man and a woman."2 The Catholic Church responded to the recent ruling with outrage. As Archbishop Anuar Battisti put it, the Supreme Court's decision

  4. #4 peak

    taller growth. Too much direct sunlight can scorch the leaves. Put them 3 to 4 feet away from a bright window, or shade the window lightly with a sheer curtain.⏎Keep the room temperature between 65 and 80

  5. #5 peak

    eagle shrieks and leopard growls), the researchers found greater complexity in expression than previously understood as well as differences in alarm calls between the two locations.⏎Confirming with linguistic means some hypotheses initially made by primatologists, their analysis showed that these

  6. #6 peak

    How many times like this are there between midnight⏎and 7 a.m.?⏎These practical challenges are all about making a 'tray' and covering it with paper.⏎My cousin was 24 years old on Friday April 5th

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 not a fan of this. I am not a fan of this. I am not a fan of this. I am not a fan of this. I am not a fan of this. I am not a fan of this.

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

    Stage - A guide for parents'. This outlines information for each phase of development aligned with each area of learning and also shares ideas on how you can support your child at home. Here are some key pages that may be of particular use:⏎Pages

  2. #2 peak

    making appointments with them and any typical front desk protocols.⏎- Support your child in using their voice and express any concerns they have to their doctor.⏎- Keep a

  3. #3 peak

    attractiveness to the 21st Century mind.⏎At the turn of the 20th Century raged a debate (begun in the 1870s in America) in legal circles in the US

  4. #4 peak

    across multiple pages. The pattern of rhyming two lines and ending with a dark, dark cave continues. This sets a mood. The reader is set up for something a bit spooky or mysterious in only 14 words.⏎In all three

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. L2:2762 excites
  2. L3:1837 weakly excites
  3. L5:2547 weakly excites
  4. L3:1095 weakly excites
  5. L3:122 weakly excites
  6. L1:1961 weakly suppresses
  7. L5:1021 weakly suppresses
  8. L5:2401 weakly suppresses
  9. L4:2442 weakly suppresses
  10. L5:1794 weakly excites
  11. L3:115 weakly suppresses
  12. L5:1164 weakly excites unclear: weak, word-piece and 'Note' labels
  13. L2:2824 weakly excites
  14. L0:483 weakly excites
  15. L4:2452 weakly excites
  16. L3:2441 weakly suppresses
  17. L3:2174 weakly suppresses
  18. L5:1401 weakly suppresses
  19. L1:1960 weakly excites
  20. L3:1385 weakly excites
  21. L4:1845 weakly suppresses
  22. L5:1254 weakly excites
  23. L5:659 weakly excites
  24. L3:63 weakly excites

Feeds later layers

  1. L9:1340 excites
  2. L13:1237 excites
  3. L17:2667 excites
  4. L14:1953 excites
  5. L15:1836 excites
  6. L13:831 excites
  7. L14:2374 excites
  8. L14:2022 excites
  9. L12:2685 suppresses
  10. L15:527 suppresses
  11. L15:2443 excites
  12. L7:428 excites
  13. L17:2355 excites
  14. L20:1525 excites
  15. L8:984 suppresses
  16. L10:2488 weakly excites
  17. L17:1721 weakly excites 'by' introducing a method or means
  18. L23:2763 weakly excites
  19. L11:2015 weakly excites
  20. L16:1717 weakly excites
  21. L8:390 weakly excites "a" after sentence-opening "As"
  22. L12:719 weakly excites
  23. L17:1839 weakly excites
  24. L8:1901 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.

3 values between -1.34 and -1.162 values between -1.16 and -0.987 values between -0.98 and -0.803 values between -0.80 and -0.6216 values between -0.62 and -0.4393 values between -0.43 and -0.25720 values between -0.25 and -0.072339 values between -0.07 and 0.11640 values between 0.11 and 0.2963 values between 0.29 and 0.477 values between 0.47 and 0.652 values between 0.65 and 0.833 values between 0.83 and 1.012 values between 1.01 and 1.191 values between 1.37 and 1.551 values between 1.55 and 1.731 values between 1.73 and 1.911 values between 2.46 and 2.641 values between 2.82 and 3.001 values between 3.00 and 3.181 values between 3.90 and 4.081 values between 5.71 and 5.89offnegativepositiveoften

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. FontAwesome
  2. 什麽
  3. 阿拉伯
  4. mere
  5. parenthesis
  6. MBER
  7. トー
  8. )}.
  9. казал
  10. COME

Suppresses

  1. noqa
  2. .TODO
  3. antaged
  4. pliant
  5. tractor
  6. �能
  7. TRL
  8. icult
  9. ports
  10. ritic