Neuron Explorer

Qwen3-0.6B

noun right after a possessive

A neuron in layer 1 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 responds to the word that comes right after 'my', 'her', 'his' or 'their', such as 'readers' in 'my readers' or 'audience' in 'his audience'. It is weaker and sometimes negative on places or people after possessives like 'my apartment'. Turning it up did not produce a clear theme.

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

    my readers will be surprised or even upset that Thornton puts profit at the top of her list

  2. #2 peak

    20 Images Online|⏎(48 votes cast)⏎Biggles and the team set out as part of the International Squadron to help the Finns. They stumble upon a dying Pole and become involved in a tussle with German intelligence for his

  3. #3 peak

    is kind energy coming from her. I feel light and happy, and sometimes I even feel like I’ve worked through something while in her presence.⏎I’ve experienced it during my years of practicing optometry.⏎Holding space

  4. #4 peak

    .com. Sadly they wanted someone with more experience but hey I tried right? So instead of deleting my short article I thought I would share it with my readers. I cannot use it for school purposes since I have to only use material found

  5. #5 peak

    2005 President George Bush delivered a speech designed to justify his foreign policy failures since 9/11. Throughout his talk he intoned his audience to recognize the goodness of American foreign policy and the inherent democratic character of the United

  6. #6 peak

    . As you write her words, bring her attention to the use of uppercase and lowercase letters and spacing between words.⏎“C-a

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 want to be able to do this, and I have been thinking about it a lot. I have been thinking about it again, and I have been thinking about it again again, and I have been thinking about it again again again,

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

    "As the alerts came in, my mind began to race," Jenna Wortham wrote. "Three friends, I learned, had arrived at a music venue near my apartment. But why? What was happening there? Then I saw pictures of other friends

  2. #2 peak

    EMPLOYED HERE". In the early hours of the morning, as the rioting spread north and south, Lino Rivera was picked up from his mother's apartment and photographed with a police officer. The photographs were distributed in order to prove that

  3. #3 peak

    other personal details. This also includes the name of your school, your photo or any personal information about your friends or family.⏎- Meeting people online might be fun, but remember the people you meet online

  4. #4 peak

    stays local. Users are able to communicate with their immediate surrounding communities. Neighbors can get to know each other, discuss local issues or even search for a babysitter. It was a conversation on Nextdoor that prompted us to start Tech For Non

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. L0:2789 weakly suppresses
  2. L0:1760 weakly excites
  3. L0:2333 weakly suppresses
  4. L0:1223 weakly excites
  5. L0:2107 weakly excites
  6. L0:3040 weakly suppresses
  7. L0:393 weakly excites
  8. L0:1285 weakly suppresses
  9. L0:1980 weakly excites
  10. L0:685 weakly excites
  11. L0:386 weakly suppresses
  12. L0:1180 weakly excites
  13. L0:40 weakly excites 'of' in 'sort of' hedges
  14. L0:3044 weakly excites
  15. L0:1695 weakly excites
  16. L0:362 weakly suppresses
  17. L0:1823 weakly excites
  18. L0:1986 weakly excites
  19. L0:1854 weakly excites
  20. L0:2091 weakly excites
  21. L0:1433 weakly excites
  22. L0:895 weakly excites
  23. L0:2642 weakly excites
  24. L0:677 weakly suppresses

Feeds later layers

  1. L16:686 weakly excites
  2. L4:726 weakly suppresses
  3. L13:173 weakly suppresses
  4. L7:1486 weakly suppresses
  5. L16:1885 weakly excites
  6. L18:628 weakly suppresses
  7. L12:488 weakly excites
  8. L25:2563 weakly excites
  9. L12:271 weakly excites
  10. L27:2419 weakly excites
  11. L11:1318 weakly excites
  12. L17:1318 weakly excites
  13. L24:1064 weakly suppresses
  14. L12:90 weakly excites
  15. L17:2575 weakly suppresses
  16. L13:1066 weakly suppresses
  17. L16:51 weakly suppresses
  18. L7:2072 weakly suppresses
  19. L9:2681 weakly suppresses
  20. L18:1081 weakly suppresses
  21. L4:2504 weakly suppresses
  22. L2:390 weakly excites
  23. L10:3002 weakly excites
  24. L5:981 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.

2 values between -1.55 and -1.481 values between -1.33 and -1.261 values between -1.26 and -1.191 values between -0.97 and -0.893 values between -0.89 and -0.823 values between -0.82 and -0.752 values between -0.75 and -0.687 values between -0.68 and -0.609 values between -0.60 and -0.535 values between -0.53 and -0.469 values between -0.46 and -0.3822 values between -0.38 and -0.3146 values between -0.31 and -0.24109 values between -0.24 and -0.16275 values between -0.16 and -0.09827 values between -0.09 and -0.021745 values between -0.02 and 0.06590 values between 0.06 and 0.13139 values between 0.13 and 0.2050 values between 0.20 and 0.2726 values between 0.27 and 0.3511 values between 0.35 and 0.425 values between 0.42 and 0.493 values between 0.49 and 0.574 values between 0.57 and 0.646 values between 0.64 and 0.711 values between 0.78 and 0.863 values between 0.86 and 0.931 values between 0.93 and 1.001 values between 1.08 and 1.151 values between 1.29 and 1.37offnegativepositiveoften

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. .coroutines
  2. olduğunu
  3. aturas
  4. врем
  5. -President
  6. PropertyDescriptor
  7. reative
  8. .Properties
  9. +xml
  10. Hast

Suppresses

  1. 술
  2. Lana
  3. abled
  4. pak
  5. bit
  6. ngr
  7. mits
  8. oken
  9. avax
  10. itel