Neuron Explorer

Qwen3-0.6B

unclear: word fragments, weak

A neuron in layer 10 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron responds only weakly and mostly to pieces of longer words that were split apart, like 'Zeb' in Zebulon or 'Gunn' in Gunnuk. There is no clear everyday theme, and turning it up did not reveal one.

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

    Montgomery Pike⏎In mid-July 1806 Lewis and Clark were on their way back from the Pacific. At the same time young army Lieutenant Zebulon Montgomery Pike left St. Louis with twenty-three men to reconnoiter

  2. #2 peak

    the waterway. A village steeped in Native tradition and pride, the people live in harmony with the bears as they frequent the area during salmon runs. Gunnuk Creek watershed is a vital source of subsistence for the people of Kake,

  3. #3 peak

    God can use imperfect people for His purposes. Christ<|endoftext|>Published on November 23rd, 2008 | by What2Learn0⏎Printable coloring pages – the alphabet⏎Free coloring pages to print for kids to help them

  4. #4 peak

    different. Although the latest legs have exceeded all expectations in stress-testing–the 3-D-printed plastic is about as strong as a traditional prosthetic-–coons and associate professor Matt Ratto have yet to find the perfect thickness, the

  5. #5 peak

    cost less than €1 each to produce. 10 confirmed patients have been connected to a breathing machine via a 3D printed valve.⏎Although Fracassi is<|endoftext|>Key: "S:" = Show Synset (semantic) relations,

  6. #6 peak

    in reality they are plagued with lies and evil. There appearance will make it very difficult for Hamlet to uncover the truth.⏎Polonius is constantly cncerned with his appearance. He always wants to keep up the appearance of loving 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: What is the relationship between the two things: the first one is the subject of the second one? (The second one is the object of the first one) Okay, so that is the first one. The second one is the object of

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

    lower voltage without necessarily losing power.⏎Figure 4: MPPT Charge Controller⏎Figure 5: Power Curve for a PV Panel with Charging Ranges for PWM Controllers⏎MPPT controllers are able to pull this off because

  2. #2 peak

    172.16.128.0/17 SUBNET3 : 10101100.00010001.0yyyyyyy.yyyyyyyy => 172

  3. #3 peak

    Human Development for Helping Professionals (2006, 2nd ed. ) by Patriia C.⏎John Winthrops City on a hill EssayJohn winthrops city on a hill John Winthrops 1630 speech

  4. #4 peak

    of chrysanthemum tea, which is made with crushed dried flowers and boiling water.⏎What forms of chrysanthemum are available?⏎Dried chrysanthemum flowers can be found<|endoftext|>Copyright © University of Cambridge. All

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. L6:24 strongly excites
  2. L8:258 strongly excites
  3. L5:4 strongly suppresses
  4. L9:870 excites
  5. L5:25 excites
  6. L6:115 excites
  7. L9:15 excites
  8. L3:2870 excites
  9. L9:305 suppresses
  10. L9:99 suppresses
  11. L7:1201 excites
  12. L8:1426 excites
  13. L6:169 excites
  14. L8:154 excites
  15. L9:536 suppresses
  16. L3:22 suppresses
  17. L8:677 weakly excites
  18. L5:187 weakly excites
  19. L6:198 weakly suppresses
  20. L6:148 weakly excites
  21. L9:254 weakly excites
  22. L5:498 weakly suppresses
  23. L6:374 weakly suppresses
  24. L5:36 weakly suppresses

Feeds later layers

  1. L13:2270 strongly suppresses
  2. L12:623 suppresses
  3. L13:105 suppresses
  4. L11:1191 excites
  5. L13:260 excites
  6. L12:134 excites
  7. L14:185 excites
  8. L15:118 excites
  9. L14:697 excites
  10. L12:243 excites
  11. L12:1307 suppresses
  12. L12:1217 excites
  13. L14:224 excites
  14. L12:1042 excites
  15. L11:2437 excites
  16. L14:98 excites
  17. L13:606 excites
  18. L11:779 excites
  19. L11:1701 excites
  20. L14:508 suppresses
  21. L14:74 excites
  22. L11:70 suppresses
  23. L11:908 suppresses
  24. L13:381 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 -1.27 and -1.221 values between -0.99 and -0.941 values between -0.94 and -0.894 values between -0.89 and -0.841 values between -0.84 and -0.801 values between -0.80 and -0.751 values between -0.75 and -0.701 values between -0.65 and -0.616 values between -0.61 and -0.5610 values between -0.56 and -0.518 values between -0.51 and -0.4712 values between -0.47 and -0.429 values between -0.42 and -0.3721 values between -0.37 and -0.3234 values between -0.32 and -0.2848 values between -0.28 and -0.2367 values between -0.23 and -0.18129 values between -0.18 and -0.13216 values between -0.13 and -0.09468 values between -0.09 and -0.041429 values between -0.04 and 0.01874 values between 0.01 and 0.06315 values between 0.06 and 0.10121 values between 0.10 and 0.1567 values between 0.15 and 0.2035 values between 0.20 and 0.2511 values between 0.25 and 0.298 values between 0.29 and 0.343 values between 0.34 and 0.392 values between 0.39 and 0.433 values between 0.43 and 0.481 values between 0.58 and 0.62offnegativepositiveoften

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. PickerController
  2. цев
  3. aceous
  4. acious
  5. füh
  6. ulla
  7. �
  8. Cock
  9. ятия
  10. klä

Suppresses

  1. fi
  2. Topic
  3. ined
  4. g
  5. istent
  6. .VisualStudio
  7. ersh
  8. !';⏎
  9. verity
  10. 你自己