Neuron Explorer

Qwen3-0.6B

"past" or "passed" after motion verbs

A neuron in layer 4 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 words like "past", "passes" and "by" when something moves or time goes by, as in "slip past your defenses" or "months went by". Turning it up made the text wander into unrelated stories and memories.

Written by Claude from this neuron's activations and steering outputs. Confidence: high. 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

    At some point, you are going to get sick. Despite taking such precautions as frequent hand washing or carrying around hand sanitizer, sometimes a germ sneaks its way past your defenses and lodges its way in your system. When that happens, you

  2. #2 peak

    UR: I HAVE the honor to inform you that Florida and the Lucayan Islands are situate on one side of the Bahama (old) Channel, which passes between Havanna (Cuba) and Florida. But nearer the […]⏎Con

  3. #3 peak

    See for Yourself⏎If you just want to glimpse the buttes as you whiz past in your car, the easiest thing to do is to simply take a drive along

  4. #4 peak

    Just as human germs vary, your computer may become infected with something minor - like a trojan - or major - like a worm. When something does slip past your defenses and infects your system, there are steps you can take to get

  5. #5 peak

    of an Indian chieftain first appeared on the supporters’ flag of the KAA Gent football club in 1924⏎Nevertheless, many years passed between Buffalo Bill’s visit to Belgium in 1906 and the use

  6. #6 peak

    , and Gundaphorus gave him a large quantity of money for building the palace, and continued to send him large quantities of money and provisions as the months went by. But Thomas took all the money and provisions he received from Gundaphorus and

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: a bit. The problem is to find a balance of a static system with some sort of aspect. The problem is to find a very basic system with a single population. The population is initially filled with with the first reservoir of a chemical system

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

    something new together — cheer for the good guys and boo the bad ones in the books you read. You also get a peek into how your child sees the world through the comments she makes on the plot, the characters, and the setting. “

  2. #2 peak

    exploring the cosmos through a variety of telescopes that they acquire, maintain, and improve on their own. Some of these amateur astronomers specialize in capturing what is seen through their telescopes in images and are astrophotographers.⏎What happens when the

  3. #3 peak

    proofs, not through the formulaic method that seems to be so popular right now. Mr. Sheen bases his exploration of geometry on the tenet that experience through drawing is of great value to a student, and I couldn’t agree more.

  4. #4 peak

    Becoming good at math begins long before a child enters school. Even babies can understand simple math, such as noticing patterns. Toddlers love learning math through puzzles and games, such as comparing sizes and shapes. These concepts help them make

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. L3:1963 suppresses
  2. L3:1545 weakly suppresses
  3. L2:2671 weakly suppresses
  4. L3:50 weakly excites
  5. L3:2111 weakly excites
  6. L3:1502 weakly excites
  7. L2:1657 weakly excites
  8. L3:2071 weakly excites
  9. L3:2989 weakly suppresses
  10. L2:70 weakly excites
  11. L2:2096 weakly excites
  12. L3:2162 weakly suppresses
  13. L0:947 weakly excites
  14. L1:2944 weakly excites
  15. L1:2131 weakly excites
  16. L0:2277 weakly excites
  17. L3:2615 weakly suppresses
  18. L2:2963 weakly suppresses
  19. L3:186 weakly suppresses
  20. L1:491 weakly excites
  21. L3:2700 weakly suppresses
  22. L2:3000 weakly excites
  23. L3:1860 weakly excites
  24. L0:768 weakly suppresses

Feeds later layers

  1. L7:2586 excites
  2. L8:1484 excites
  3. L19:2420 excites
  4. L5:2602 excites
  5. L25:2169 weakly excites
  6. L20:1122 weakly excites
  7. L5:1705 weakly suppresses
  8. L6:2014 weakly excites
  9. L7:2374 weakly suppresses
  10. L19:685 weakly suppresses
  11. L25:1646 weakly excites
  12. L17:1139 weakly suppresses
  13. L15:1066 weakly suppresses
  14. L11:439 weakly suppresses
  15. L6:2958 weakly excites the colon after Note at the start of a note
  16. L5:1050 weakly suppresses
  17. L15:1358 weakly excites 'process' after 'is a' definitions
  18. L10:1553 weakly suppresses
  19. L21:2895 weakly excites
  20. L7:2255 weakly excites
  21. L5:2567 weakly suppresses
  22. L18:1805 weakly suppresses
  23. L11:2958 weakly excites
  24. L19:683 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 -2.49 and -2.271 values between -0.94 and -0.724 values between -0.72 and -0.50131 values between -0.50 and -0.281549 values between -0.28 and -0.062082 values between -0.06 and 0.17131 values between 0.17 and 0.395 values between 0.39 and 0.611 values between 0.61 and 0.831 values between 3.05 and 3.271 values between 3.93 and 4.151 values between 6.15 and 6.37offnegativepositiveoften

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. yü
  2. passing
  3. passes
  4. Boeh
  5. oshi
  6. 多年的
  7. Woche
  8. registr
  9. entity
  10. MANY

Suppresses

  1. zig
  2. .RequestBody
  3. ièrement
  4. azaar
  5. @ResponseBody
  6. uncated
  7. 在线咨询
  8. 聚焦
  9. -sided
  10. responseObject