Neuron Explorer

Qwen3-0.6B

the '0' in 360

A neuron in layer 3 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 responds to the number 360, specifically the last digit, as in '360 camera' or '360 degrees'. Turning it up did not bring out this theme 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

    look, just as I am sure you can picture a bar code in your mind just by my mentioning them.⏎I created a video that transitions through 360 QR Codes so you can begin to see what changes, and what stays the same

  2. #2 peak

    converts rotary motion into linear motion.⏎The ‘lead’ of a Lead Screw is the distance which a Lead Screw Nut will move during one 360° rotation of the screw. A smaller Lead results in a tighter thread, which

  3. #3 peak

    . Ramnarine has also taught architecture students how to use 360 technology to visualize projects.⏎“We showed them how to take 360 photos

  4. #4 peak

    Luksatrio is using to create his virtual tour project. Once it’s complete, he’ll create a manual for future students to use 360 cameras and begin introducing the technology into their program.⏎To learn more about 3

  5. #5 peak

    projects more engaging. By capturing videos and photos from every angle, it allows viewers to move and interact with the images.⏎The creative possibilities of a 360-degree camera prompted second-year professional communications student, Christo Luksatrio,

  6. #6 peak

    ] when you’re not not restricted to a single frame.”⏎The department of professional communications has purchased a 360fly, a user-friendly 360 camera, which

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 have been a detective story. I have been a criminal. I have been a recluse. I have been a recluse. I have been a reclusive hero. I have been a reclusive hero. I have been a re

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

    —Using narrow, intermediate, or broad definitions, the probandwise concordance for alcoholism was consistently higher in monozygotic than in dizygotic twin pairs. Multifactorial threshold models suggested that the heritability of

  2. #2 peak

    are some of the classes in which we should expect and reward failure: if our students don’t make mistakes, they aren’t trying anything new.⏎Science teacher Marsenne Kendall tells parents at Back-To-School night: “"I embrace mistakes!!

  3. #3 peak

    life like on the ice? Our team of six guys and two girls flew to Christchurch, New Zealand, and then were flown down to the US McMurdo base in Antarctica. We spent a week

  4. #4 peak

    ume is streaming southward from the eastern shore of Pensacola Bay.<|endoftext|>Ticks are frightening pests. In fact, these eight-legged and hard-bodied arachnids can scare even the most hardened horse owner. They are small and difficult to

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. L2:2317 excites
  2. L0:1224 weakly suppresses
  3. L0:178 weakly suppresses
  4. L0:1301 weakly suppresses
  5. L2:1312 weakly suppresses
  6. L2:3061 weakly excites
  7. L1:189 weakly suppresses
  8. L2:49 weakly suppresses
  9. L2:2328 weakly suppresses
  10. L1:951 weakly excites
  11. L1:2922 weakly excites
  12. L0:2709 weakly excites
  13. L1:331 weakly suppresses
  14. L1:112 weakly excites
  15. L2:1710 weakly suppresses
  16. L2:2256 weakly suppresses
  17. L0:248 weakly suppresses
  18. L1:247 weakly excites
  19. L2:1928 weakly excites
  20. L2:1262 weakly suppresses
  21. L1:777 weakly excites
  22. L2:2947 weakly suppresses
  23. L2:2221 weakly suppresses
  24. L0:858 weakly excites

Feeds later layers

  1. L4:1947 excites
  2. L7:1433 weakly excites
  3. L22:1574 weakly excites
  4. L21:1129 weakly excites
  5. L4:2310 weakly suppresses
  6. L10:879 weakly suppresses
  7. L5:2450 weakly excites
  8. L4:2104 weakly suppresses
  9. L9:1482 weakly excites
  10. L5:2236 weakly suppresses
  11. L20:1959 weakly excites
  12. L13:298 weakly excites
  13. L21:2608 weakly excites
  14. L19:1908 weakly excites
  15. L22:422 weakly excites
  16. L6:1358 weakly excites
  17. L4:1452 weakly excites
  18. L4:2483 weakly suppresses
  19. L19:1976 weakly excites
  20. L7:2334 weakly excites
  21. L9:2704 weakly excites
  22. L10:1226 weakly suppresses
  23. L26:2906 weakly excites
  24. L23:256 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.

1 values between -1.59 and -1.451 values between -1.32 and -1.192 values between -0.92 and -0.793 values between -0.66 and -0.5310 values between -0.53 and -0.4033 values between -0.40 and -0.26204 values between -0.26 and -0.131470 values between -0.13 and 0.001937 values between 0.00 and 0.13210 values between 0.13 and 0.2732 values between 0.27 and 0.402 values between 0.40 and 0.531 values between 0.53 and 0.661 values between 0.66 and 0.791 values between 3.57 and 3.70offnegativepositiveoften

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. 圜
  2. ='_
  3. equalTo
  4. imens
  5. =".
  6. LinkId
  7. Ey
  8. =\"/
  9. Tac
  10. TestId

Suppresses

  1. 脑
  2. ور
  3. 之
  4. ven
  5. will
  6. 走到
  7. tty
  8. すれば
  9. 必
  10. 辈