Neuron Explorer

Qwen3-0.6B

preposition right after a passive verb

A neuron in layer 8 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 lights up on a small word like 'to', 'on' or 'off' that comes right after a verb in the passive form, such as 'paid to', 'shot on' or 'ripped off'. When it was turned up, the model's text drifted into ordinary prose without a clear theme, so the steering output does not show much about it.

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

    for works that are sold for money. That is because registration helps to prove that the copyright of a work belongs to a certain author.⏎If an author gets paid to make a work for someone else, the person who pays for making the work (

  2. #2 peak

    local schools across the country engaged in efforts to improve science curriculums.⏎Under the grants announced today, the colleges and universities will each receive $1 million to $2 million over four years to improve science education in several areas, including modern

  3. #3 peak

    or less safe. Yet they were also unwanted and were prodded to leave as soon as possible. They had every incentive to do so, but getting

  4. #4 peak

    that, they are likely to be in a hostile environment.⏎Danger is a constant companion on the battlefield, and because of that, there are things that are done to save lives that aren’t as applicable in the civilian world.⏎Why Are We Ta

  5. #5 peak

    caliber Iver Johnson⏎It took two shots from a .32-caliber Iver-Johnson revolver to assassinate William McKinley. He was shot on September 6, 1901 in the late afternoon by Leon C

  6. #6 peak

    means is useless, I don’t believe that they can be properly roasted at home. Folks, there are educated professionals who acquire specialty equipment and are hipped on this subject. Do you think you’ll be able to properly roast coffee beans using

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: (x+1) where yz and zy. The problem is to find for the variables. Wait, no. I need to find the right part. Wait, no. I need to find the right part. Hmm,

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

    Sunday night at the age of 88.⏎Rubin, who did much of her work at the Carnegie Institution, has been called a “national treasure” by the organization’s president. During the ’60s and ’70s

  2. #2 peak

    lawyers and teachers. This undisciplined lot went on to brave bullets, were jailed, lathi-charged and suffered untold humiliations at the hands of the colonial rulers. In other words, nationalism and patriotism in India was constructed as

  3. #3 peak

    create a culture where sexual violence is prevented and reporting is encouraged.⏎This issue is current and demands attention. Vanessa Guillen, an Army Specialist, was recently killed by a fellow Specialist in Fort Hood, Texas. After she went missing, her family

  4. #4 peak

    garment that Bella Hadid wore, which was a spray-on dress. Hadid walked slowly onto a platform in the middle of the runway. Here she was sprayed by two technicians with a white material. With a little cutting and folding, the material

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. L7:345 suppresses
  2. L7:1813 excites
  3. L6:2485 weakly excites
  4. L6:12 weakly excites
  5. L4:37 weakly suppresses
  6. L3:115 weakly suppresses
  7. L5:2896 weakly suppresses
  8. L4:1494 weakly excites
  9. L7:174 weakly suppresses
  10. L6:412 weakly suppresses
  11. L4:1394 weakly excites
  12. L6:7 weakly suppresses
  13. L2:956 weakly suppresses
  14. L7:1629 weakly excites
  15. L0:1704 weakly suppresses
  16. L7:2618 weakly excites
  17. L1:2801 weakly excites
  18. L6:2790 weakly suppresses
  19. L5:2890 weakly suppresses
  20. L6:2131 weakly excites
  21. L1:2519 weakly suppresses
  22. L5:2114 weakly excites unclear: calculus notation, mixed topics
  23. L2:1899 weakly excites
  24. L4:1318 weakly suppresses

Feeds later layers

  1. L15:2606 suppresses
  2. L9:1562 suppresses 'by' before a byline or agent
  3. L9:1627 suppresses
  4. L11:361 suppresses
  5. L13:1515 suppresses "your" before doctor or health provider
  6. L19:2845 suppresses
  7. L9:1842 suppresses
  8. L19:2853 suppresses
  9. L19:2508 suppresses
  10. L16:2208 suppresses
  11. L15:799 suppresses
  12. L12:2887 suppresses
  13. L15:1053 excites
  14. L17:2197 suppresses
  15. L12:2014 suppresses
  16. L12:2145 excites
  17. L15:1455 suppresses
  18. L20:1794 suppresses
  19. L17:978 weakly suppresses
  20. L15:3044 weakly suppresses
  21. L13:2832 weakly suppresses "by" after a passive verb
  22. L14:2508 weakly suppresses
  23. L9:1830 weakly suppresses
  24. L12:1286 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 -3.89 and -3.731 values between -1.99 and -1.831 values between -1.67 and -1.521 values between -1.36 and -1.203 values between -1.04 and -0.883 values between -0.88 and -0.7310 values between -0.73 and -0.5714 values between -0.57 and -0.41186 values between -0.41 and -0.25851 values between -0.25 and -0.092001 values between -0.09 and 0.07674 values between 0.07 and 0.22118 values between 0.22 and 0.3819 values between 0.38 and 0.548 values between 0.54 and 0.703 values between 0.70 and 0.865 values between 0.86 and 1.012 values between 1.01 and 1.173 values between 1.17 and 1.332 values between 1.33 and 1.491 values between 1.49 and 1.651 values between 2.28 and 2.44offnegativepositiveoften

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. quences
  2. Украины
  3. Richie
  4. 和个人
  5. 的身体
  6. обучения
  7. 实事
  8. печат
  9. BUSINESS
  10. ัว

Suppresses

  1. [&](
  2. }};⏎
  3. directors
  4. iners
  5. '};⏎
  6. iting
  7. igator
  8. '=',
  9. 监管部门
  10. '));⏎