Neuron Explorer

Qwen3-0.6B

unclear: mid-phrase function words

A neuron in layer 3 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 fires on small words in the middle of a sentence, like 'a', 'more', 'in' or a comma, where the sentence is still unfinished. No single clear topic stands out, and turning it up did not produce a clear change in what the model wrote.

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

    P and Q are the feet⏎of the perpendiculars from X to the sides of a right angled⏎triangle. What position of X makes the length of PQ a minimum?⏎The circumcentres of four triangles are joined to form a⏎qu

  2. #2 peak

    all of the organelles and their functions. One fun—and tasty!—way to make the parts of the cell more concrete for students is to create edible cells. Using materials such as Jell-O

  3. #3 peak

    health consequences of teen sex, using measures of self-esteem and depression. The results of her work, published last May in The American Journal of Sociology, put her in the media spotlight. The New York Times showcased her study in a June article.⏎

  4. #4 peak

    . Throughout the years, the panels were also painted to cover discrepancies; two of them, including Romeo and Juliet, had faux finishes applied. Conservators concluded that all layers

  5. #5 peak

    1-2 hours depending on the size of your jar. A full melt pool will reach a depth of 1/2 inch. This will allow the fragrance to disperse more completely into the room. (Remember burn your candles for a maximum

  6. #6 peak

    , mind maps can make the job easier and less time-consuming.⏎Moreover, mind maps simplify problem-solving and planning. They

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 need to be more specific, and, I need to be more practical, and, I need to be more clear. Let me think. It's a bit a bit a bit a bit a bit a bit a bit a bit a

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

    25 to specifically target drivers in this age group.⏎* Since 1995, more than 400,000 young adults have learned life-saving defensive driving skills through DDC-Alive at 25.⏎

  2. #2 peak

    Nearly 7,000 people have been displaced and more than 5,000 homes destroyed, damaged or

  3. #3 peak

    e’s team demonstrated its principle with three lasers, but such crystals could store holograms created by up to a thousand lasers, which will allow more elaborate structures to be built. The crystals can also hold many holograms at the same time, each

  4. #4 peak

    weight loss by making the body absorb fewer calories from other foods. Studies show that doubling your daily fiber intake can result in up to 130 fewer calories being absorbed. You can add fiber to your food by making little changes to your diet

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. L1:454 excites
  2. L0:150 suppresses
  3. L2:837 excites
  4. L2:179 excites comma after a clause subject
  5. L2:307 suppresses
  6. L2:63 excites
  7. L2:1205 excites
  8. L1:604 excites
  9. L2:339 suppresses
  10. L2:104 weakly excites
  11. L1:940 weakly suppresses
  12. L2:325 weakly excites
  13. L0:896 weakly suppresses
  14. L1:969 weakly suppresses
  15. L2:93 weakly suppresses
  16. L2:501 weakly excites
  17. L2:1243 weakly excites
  18. L2:80 weakly excites
  19. L1:136 weakly suppresses
  20. L0:632 weakly excites
  21. L2:185 weakly excites
  22. L1:959 weakly excites
  23. L2:219 weakly excites
  24. L2:747 weakly excites

Feeds later layers

  1. L4:211 excites
  2. L4:44 excites
  3. L4:161 suppresses
  4. L5:460 suppresses
  5. L6:335 suppresses
  6. L4:462 excites
  7. L5:1425 suppresses
  8. L10:724 excites
  9. L4:371 suppresses
  10. L6:1579 suppresses
  11. L6:2058 suppresses
  12. L8:197 suppresses
  13. L18:729 excites
  14. L4:374 suppresses
  15. L5:1371 excites
  16. L14:591 suppresses
  17. L8:444 excites
  18. L8:183 excites
  19. L5:56 weakly suppresses
  20. L7:386 weakly suppresses
  21. L5:131 weakly excites
  22. L4:80 weakly excites
  23. L6:342 weakly suppresses
  24. L6:2704 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 -2.81 and -2.692 values between -1.95 and -1.831 values between -1.70 and -1.582 values between -1.58 and -1.462 values between -1.46 and -1.336 values between -1.33 and -1.219 values between -1.21 and -1.086 values between -1.08 and -0.9612 values between -0.96 and -0.8413 values between -0.84 and -0.7121 values between -0.71 and -0.5926 values between -0.59 and -0.4743 values between -0.47 and -0.3490 values between -0.34 and -0.22309 values between -0.22 and -0.101814 values between -0.10 and 0.03777 values between 0.03 and 0.15390 values between 0.15 and 0.28228 values between 0.28 and 0.4091 values between 0.40 and 0.5235 values between 0.52 and 0.6510 values between 0.65 and 0.777 values between 0.77 and 0.893 values between 0.89 and 1.025 values between 1.02 and 1.141 values between 1.14 and 1.261 values between 1.64 and 1.761 values between 1.88 and 2.012 values between 2.01 and 2.13offnegativepositiveoften

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. 一大
  2. cabin
  3. aturas
  4. Cabin
  5. ieurs
  6. swith
  7. actors
  8. ()].
  9. porto
  10. apos

Suppresses

  1. Solution
  2. сай
  3. AW
  4. vê
  5. AYOUT
  6. b
  7. B
  8. لق
  9. 嘬
  10. ATA