Neuron Explorer

Qwen3-0.6B

'not' in 'but not limited to'

A neuron in layer 16 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 mostly fires on the word 'not' in the phrase 'but not limited to', which is a common way to say a list is incomplete. It also fires on a few unrelated words like 'Credit' and 'Protect'. Turning it up did not produce a clear theme in the writing.

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

    a common food source for many Native American tribes including but not limited to the Iroquois, Algonquin, Ojibwa

  2. #2 peak

    documents for those who are going to build it for you and also for legal purposes. We will cover all these things in details. Some of the topics include but not limited to:⏎- How to Plan and Draw/design Your Dream Home⏎- Understanding

  3. #3 peak

    the world’s rainforests and that frontline communities organizing against the extraction and burning of dirty fossil fuels deserve the strongest support we can offer. RAN established the Protect-an-Acre program to protect the world’s forests and the rights of their inhabitants

  4. #4 peak

    and pesticides, extensive soil erosion, pollution, and high rates of greenhouse gas emissions. Low-intensity farming methods on the other hand–which include, but aren’t limited to, organic agriculture–typically favour more environmentally-friendly farming practices at the expense

  5. #5 peak

    domains, known as the acceptor and the donor layers. Excitons, the energy particles created by solar cells, must be able to travel quickly

  6. #6 peak

    repeat it at any time. Just add a new Alka-Seltzer tablet and watch as the colored bubbles rise again!⏎2. Lemon Volcano⏎Image Credit: sixthbloom.com⏎Lemon volcanoes don’t create a gigantic eruption

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 a 1 1 1, and I have a 1, one, one, one, one, ONE, that is, that is, that is, that is, that is, that that is, that is

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

    production.2⏎That support has paid off: the state is one of the nation’s leading producers of biofuels, pumping out over 1.2 billion gallons per year.3⏎However, all is not well on the policy front

  2. #2 peak

    a site on Crete known for its remarkably cool and stable conditions.⏎They recovered DNA in teeth from 32 individuals who died between 2290<|endoftext|>Module 7: Molecular Computing with RNA Sequences⏎Intron/Exon

  3. #3 peak

    accounted for the population of adults who reported mobility issues in the NTS).⏎So, car trips for 1 mile or under add up to 1.8 billion miles a year… and that’s just in England.⏎These short journeys

  4. #4 peak

    warming _ precious water. Officials say the system could end up saving 20 percent of the water Spain uses for irrigation today _ a whopping 1.3 trillion gallons of water per year.⏎It is a major milestone for a country that is

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. L15:12 strongly suppresses
  2. L8:20 excites
  3. L10:50 suppresses
  4. L13:33 suppresses
  5. L8:7 suppresses
  6. L8:4 suppresses
  7. L6:13 suppresses
  8. L9:13 suppresses
  9. L6:19 excites second half of proper names
  10. L6:7 excites
  11. L6:16 suppresses
  12. L6:12 suppresses
  13. L6:8 excites
  14. L0:1224 excites
  15. L8:14 suppresses
  16. L4:133 suppresses
  17. L12:713 excites
  18. L8:10 suppresses
  19. L1:2683 suppresses
  20. L5:198 suppresses unclear: weak "and" in lists
  21. L1:951 suppresses
  22. L8:16 excites
  23. L5:50 suppresses
  24. L5:102 suppresses

Feeds later layers

  1. L22:332 excites
  2. L21:110 excites
  3. L25:182 excites
  4. L25:854 suppresses
  5. L24:371 excites
  6. L19:418 excites
  7. L19:1057 suppresses
  8. L24:8 excites
  9. L19:258 excites
  10. L26:1451 excites
  11. L19:785 excites
  12. L20:761 excites
  13. L19:311 suppresses
  14. L19:848 suppresses
  15. L19:43 suppresses
  16. L17:1409 suppresses
  17. L17:529 suppresses
  18. L19:2850 suppresses
  19. L27:428 suppresses
  20. L18:1048 suppresses
  21. L18:2741 suppresses
  22. L19:814 suppresses
  23. L19:737 suppresses
  24. L19:2519 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 -5.99 and -5.741 values between -5.74 and -5.491 values between -5.25 and -5.001 values between -4.75 and -4.502 values between -4.50 and -4.265 values between -4.26 and -4.019 values between -4.01 and -3.7610 values between -3.76 and -3.5115 values between -3.51 and -3.2725 values between -3.27 and -3.0236 values between -3.02 and -2.7746 values between -2.77 and -2.5273 values between -2.52 and -2.2886 values between -2.28 and -2.03143 values between -2.03 and -1.78172 values between -1.78 and -1.53207 values between -1.53 and -1.29278 values between -1.29 and -1.04328 values between -1.04 and -0.79355 values between -0.79 and -0.54325 values between -0.54 and -0.30350 values between -0.30 and -0.05322 values between -0.05 and 0.20264 values between 0.20 and 0.45199 values between 0.45 and 0.69180 values between 0.69 and 0.94149 values between 0.94 and 1.19109 values between 1.19 and 1.4471 values between 1.44 and 1.6847 values between 1.68 and 1.9334 values between 1.93 and 2.1824 values between 2.18 and 2.4310 values between 2.43 and 2.6713 values between 2.67 and 2.926 values between 2.92 and 3.174 values between 3.17 and 3.426 values between 3.42 and 3.661 values between 3.66 and 3.91offnegativepositiveoften

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. (std
  2. 万
  3. static
  4. urrenc
  5. fbe
  6. lever
  7. тив
  8. overloaded
  9. ComVisible
  10. eparator

Suppresses

  1. ness
  2. 江区
  3. HEAP
  4. breakdown
  5. Cook
  6. sist
  7. �
  8. ien
  9. raq
  10. eref