Neuron Explorer

Qwen3-0.6B

"wide" after a measurement

A neuron in layer 4 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 lights up on the word "wide" when it describes how broad something is, such as "25 feet wide" or "a wide range". Turning it up made the model write unrelated text, so the steering did not show this.

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

    sand or loam soil. Mature specimens typically range from 20 to 30 feet high and up to 25 feet wide. Eastern redbud has a uniform, vase-shaped habit with multiple trunks

  2. #2 peak

    id lowland coastal region, the central high sierra of the Andes, and the dense forest of the Amazon. A wide range of important mineral resources are found in the mountainous and coastal areas, and

  3. #3 peak

    Hawaii and California. We discovered that the conventional method of measuring ocean plastic, using nets of less than a meter (3 ft) wide, was inaccurate because it seriously underestimated the total amount of plastic. The reason for

  4. #4 peak

    ! There’s more…⏎How Science Works has been adapted as an online course for middle- and high-school science educators to “broaden their own knowledge and understanding and to use with students, the course weaves together

  5. #5 peak

    –22" tall⏎Variety Information: Large, dark green oval leaves with serrated edges up to 10" long, and 8" wide⏎Attributes: Good for Containers⏎When to Sow Outside: RECOMMENDED

  6. #6 peak

    actually glass set in a steel frame set in the wooden door a method that was at that time also used in palaces in Budapest and Vienna.⏎15 meter wide at the front and 65 meters deep it has 500 square

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: (6.0.2.1.1.1.1) I think about the number How to pick the best I am really confused to the fact Which is the best time to get together to think about

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

    is the main ingredient in your diet.⏎Food is food insofar as our tastes are concerned. But, when it comes to our stomachs, and, by extension, our whole body is involved, food is more than just food. It’s

  2. #2 peak

    your tree is essential to its health and survival for the first few years after it’s been planted. Watering slowly and deeply is better for your tree’s over-all health then fast and frequent waterings. Watering before 10 a.m

  3. #3 peak

    marshes and clappers in salt. The two birds overlap in brackish water marshes, and they do hybridize. Clapper rails are darker over all, with a mix of grays and deep browns that kings don’t have

  4. #4 peak

    If people mimic or follow someone else’s<|endoftext|>|Image Credit :|⏎Delhi, officially the capital territory of India is a collection of a number of cities spread across the metropolitan region and has been continuously inhabited since the 6th century BC.

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. L2:2273 suppresses
  2. L3:272 weakly excites
  3. L3:2925 weakly suppresses
  4. L2:2400 weakly suppresses
  5. L1:1464 weakly excites
  6. L3:573 weakly excites
  7. L3:691 weakly excites
  8. L3:2037 weakly suppresses
  9. L3:2482 weakly excites
  10. L2:111 weakly suppresses
  11. L3:2508 weakly suppresses
  12. L2:2328 weakly suppresses
  13. L3:122 weakly excites
  14. L2:1036 weakly excites
  15. L3:102 weakly suppresses
  16. L3:464 weakly excites
  17. L2:1827 weakly excites
  18. L0:3016 weakly excites
  19. L3:187 weakly excites
  20. L2:2736 weakly suppresses
  21. L3:1525 weakly excites
  22. L2:2725 weakly suppresses
  23. L0:1224 weakly suppresses
  24. L2:75 weakly suppresses

Feeds later layers

  1. L24:2779 excites
  2. L8:1466 excites
  3. L7:2489 excites
  4. L22:2961 excites
  5. L27:1610 weakly excites
  6. L26:1154 weakly excites
  7. L5:1087 weakly excites
  8. L18:374 weakly excites
  9. L15:927 weakly excites
  10. L19:323 weakly suppresses
  11. L19:1340 weakly excites
  12. L5:1806 weakly excites
  13. L7:2741 weakly suppresses
  14. L8:1274 weakly excites
  15. L18:2892 weakly excites
  16. L10:1033 weakly excites
  17. L22:1838 weakly suppresses
  18. L22:2453 weakly suppresses
  19. L5:1247 weakly excites
  20. L18:919 weakly suppresses
  21. L20:470 weakly suppresses
  22. L8:2986 weakly suppresses
  23. L26:2129 weakly suppresses
  24. L18:533 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.

7 values between -0.82 and -0.50226 values between -0.50 and -0.193455 values between -0.19 and 0.12207 values between 0.12 and 0.435 values between 0.43 and 0.741 values between 0.74 and 1.061 values between 1.06 and 1.371 values between 1.37 and 1.681 values between 1.68 and 1.991 values between 2.61 and 2.921 values between 7.60 and 7.911 values between 9.16 and 9.471 values between 11.34 and 11.65offnegativepositiveoften

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. →width
  2. (width
  3. wider
  4. width
  5. .width
  6. WIDTH
  7. """⏎⏎⏎
  8. width
  9. """
  10. widen

Suppresses

  1. ride
  2. .GetObject
  3. ign
  4. 干事
  5. ivol
  6. 红星
  7. Ronnie
  8. volumes
  9. rides
  10. .ISupportInitialize