Neuron Explorer

Qwen3-0.6B

unclear: words that set up a qualifier

A neuron in layer 13 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 that set up a qualification or a contrast, like 'may', 'but', 'conversely' or 'in the carefully selected patient'. Turning it up made the text wander into unrelated topics, so it does not clearly control anything visible.

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

    precisely remove material to produce two smooth surfaces that are parallel with each other and to the hub-mounting surface. The problem with thickness variation is that too much material may need to be removed to establish these surfaces, leaving the rotors below the minimum

  2. #2 peak

    of sunscreen have minimized the amount of vitamin D that many of us get from sun exposure. Calcium is essential for strong bones and a healthy heart, but too much is not good.⏎In fact, excess calcium, which the NIH describes as more than

  3. #3 peak

    eight weeks, which isn't always "just gas." By then, your baby will show pleasure at the sight and sound of their parents, and may get sad when they don't see them.⏎- Step 6: Look for cause and effect

  4. #4 peak

    yet most biological movements involve a large number of degrees of freedom (in a rigid arm this number is directly related to the number and type of joints). An extreme case with especially high degrees of freedom is given by systems in which muscles are unattached

  5. #5 peak

    30. It tells you the oil’s thickness or viscosity. A thinner motor oil — indicated by a lower number — flows more easily. Conversely, a thicker oil — with a larger number — is thick and resistant to flow.

  6. #6 peak

    method in which the muscles and tendons are stretched around the fractured bone to help align it. Surgery for a broken bone isn’t always required, but may be needed to support and position bone fragments.⏎Hernando Orthopaedic provides expert fracture

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 working with the code, to let me to the to the... I... I... to the... for to... in a way to... to the... to... in a way to... to the... to... to...

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

    caves at the Wonderland of Rocks, take the place seriously. The average altitude is 4,400 feet and there are dramatic temperature extremes between day and night. Bring layers to dress up and down for temperature shifts. The terrain is more

  2. #2 peak

    should also considered. This is the trick you should apply. Do you want a garden contoured hill (hill), normal (flat), terraced, or variations? But remember, everything should fit your needs.⏎Afterwards, do not forget to

  3. #3 peak

    ford breed which was founded in the mid-18th century by the farmers of Hereford County, England. Among the horned Herefords an occasional calf would be born which did not develop horns. This change from parents' characteristics is

  4. #4 peak

    point about your example or thing. For example, if you are writing up a newspaper about mobile phones, you might be requested to compare sales reports from two different models. Similarly, if you’re analyzing the affects of smoking on children’s asthma,

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. L12:2041 suppresses
  2. L12:2281 excites
  3. L12:764 suppresses
  4. L11:1960 suppresses
  5. L11:841 suppresses
  6. L11:998 excites
  7. L12:1356 suppresses
  8. L12:836 suppresses
  9. L12:2016 suppresses
  10. L12:690 excites
  11. L12:2917 excites
  12. L12:1991 suppresses
  13. L11:999 excites
  14. L12:1894 excites
  15. L12:1280 suppresses
  16. L12:122 excites unclear: word before a clause continues
  17. L12:798 excites
  18. L12:2942 suppresses
  19. L12:105 excites
  20. L12:683 excites
  21. L11:644 suppresses
  22. L12:1248 excites
  23. L8:135 excites
  24. L12:913 suppresses

Feeds later layers

  1. L14:2536 suppresses
  2. L14:2206 excites
  3. L14:1740 suppresses
  4. L15:772 excites
  5. L15:1446 excites
  6. L14:2655 excites
  7. L15:1790 suppresses
  8. L14:1686 suppresses
  9. L16:3059 excites
  10. L15:2010 excites
  11. L14:346 excites
  12. L14:1161 excites
  13. L14:1756 excites
  14. L14:2223 excites
  15. L14:2771 excites
  16. L14:2875 suppresses
  17. L14:2307 excites
  18. L14:2873 suppresses
  19. L15:2399 suppresses
  20. L14:1795 excites
  21. L14:482 excites
  22. L14:1150 excites
  23. L16:2265 excites
  24. L15:1705 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.

3 values between -2.00 and -1.851 values between -1.85 and -1.692 values between -1.53 and -1.381 values between -1.38 and -1.223 values between -1.22 and -1.0714 values between -1.07 and -0.919 values between -0.91 and -0.7539 values between -0.75 and -0.6076 values between -0.60 and -0.44215 values between -0.44 and -0.28575 values between -0.28 and -0.131827 values between -0.13 and 0.03706 values between 0.03 and 0.19205 values between 0.19 and 0.3495 values between 0.34 and 0.5046 values between 0.50 and 0.6527 values between 0.65 and 0.8124 values between 0.81 and 0.979 values between 0.97 and 1.1210 values between 1.12 and 1.285 values between 1.28 and 1.434 values between 1.59 and 1.751 values between 1.90 and 2.062 values between 2.06 and 2.221 values between 2.22 and 2.371 values between 2.53 and 2.682 values between 2.68 and 2.841 values between 2.84 and 3.001 values between 3.00 and 3.151 values between 3.15 and 3.311 values between 3.47 and 3.621 values between 4.09 and 4.25offnegativepositiveoften

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. otation
  2. otope
  3. ination
  4. inations
  5. 疹
  6. oin
  7. inesis
  8. ][]
  9. okers
  10. ranges

Suppresses

  1. aq
  2. UCE
  3. >",
  4. >Action
  5. aklı
  6. 优越
  7. ba
  8. !",
  9. 蔼
  10. iệu