Neuron Explorer

Qwen3-0.6B

"per" in rate phrases

A neuron in layer 19 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 fires very clearly on the word "per" in rate phrases like "per passenger mile," "per kilometer" or "per person." It is one of the strongest and most reliable triggers among these five. Turning it up made the model drift into numbers and quantities, but the steering text is not a clean match.

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

    global warming pollution per person for the miles traveled (and may cost less, too).⏎On average, taking a trip by bus produces the least amount of greenhouse gas per passenger mile, followed by train travel, then air. Cars, light

  2. #2 peak

    This would combine use-phase with build-phase emissions.⏎Today, the European Union requires average carbon dioxide emissions for all new passenger cars to be 130 grams per kilometer driven. This figure is supposed to decrease by about 27

  3. #3 peak

    optimize water efficiency.⏎Greenhouse gas emissions:⏎U.S. cotton showed strong improvement in the 10-year average compared to the previous decade for GHG emissions per pound of lint produced.⏎The Global Cotton LCA (Cotton Incorporated,

  4. #4 peak

    s to deliver full LCA analyses of all models, to demonstrate their environmental footprint. This will probably include a sustainability cap imposed on the total amount of carbon emitted per unit from cradle to grave.⏎I also expect an increasingly demanding public to base

  5. #5 peak

    emissions and reduces landfill odors.⏎This year's LMOP winning projects will avoid the emissions of 546,000 tons of carbon dioxide equivalent per year, the equivalent of annual greenhouse gas emissions from nearly 100,

  6. #6 peak

    more, wheat up to $5 more. According to another computer model, organic farmers are expected to net an average of $50 to $60 more per acre than their conventional counterparts.<|endoftext|>It is sometimes felt that saving energy by natural

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: the way that a writer's response to a question is a response to the question itself. That is, the question is the writer's response to the question, and the response is a response to the question. The question is the writer's

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

    . Talk to your doctor about the right medicines for you.⏎A common and safe remedy is to take supplemental vitamin B6 (pyridoxine), to a maximum of 100 mg/day. The American Congress of Obstetricians and

  2. #2 peak

    and E. coli or salmonella infection.⏎How to use⏎Use Ampicillin as directed by your doctor.⏎Take Ampicillin by mouth at least one-half hour before or 2 hours after eating.⏎Take Ampicillin with a full

  3. #3 peak

    times a month, while older crabs may take thirty to fifty days to grow large enough before needing to shed again. A newly shed crab will be about a third bigger than it was before.⏎Is my red claw crab dead or molting?⏎

  4. #4 peak

    2 inches apart.⏎- For summer turf establishment, a thin layer of mulch (no more than⏎1/4 inch thick) can be spread over the seeds with a peat spreader to

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. L18:1546 suppresses
  2. L16:1154 suppresses
  3. L8:2654 excites
  4. L15:1503 excites
  5. L17:1040 excites
  6. L10:3036 suppresses
  7. L10:2844 excites
  8. L9:2347 suppresses
  9. L10:141 excites
  10. L18:1726 suppresses
  11. L6:442 excites
  12. L15:1521 excites
  13. L15:1423 suppresses
  14. L9:43 excites
  15. L11:2874 excites
  16. L15:1926 suppresses
  17. L11:805 suppresses
  18. L12:1686 excites
  19. L13:1705 suppresses
  20. L12:408 suppresses
  21. L16:1279 suppresses
  22. L18:2183 suppresses
  23. L12:1655 suppresses
  24. L2:1018 excites

Feeds later layers

  1. L25:158 excites
  2. L20:1692 excites
  3. L21:2443 excites
  4. L21:2573 excites
  5. L22:991 excites
  6. L20:2616 excites
  7. L20:2483 excites
  8. L20:2624 excites
  9. L25:437 excites
  10. L20:1404 excites
  11. L22:941 excites
  12. L25:611 excites
  13. L23:2208 excites
  14. L22:1917 excites
  15. L24:806 excites
  16. L21:1348 excites
  17. L22:395 excites
  18. L21:1563 excites
  19. L23:1404 excites
  20. L21:1957 excites
  21. L20:232 suppresses
  22. L21:2852 weakly excites spot where a number or 'time' comes next
  23. L24:1201 weakly excites
  24. L21:1628 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.

2 values between -4.67 and -3.873 values between -3.87 and -3.064 values between -3.06 and -2.2612 values between -2.26 and -1.46194 values between -1.46 and -0.663063 values between -0.66 and 0.15492 values between 0.15 and 0.9554 values between 0.95 and 1.7529 values between 1.75 and 2.5611 values between 2.56 and 3.3614 values between 3.36 and 4.168 values between 4.16 and 4.964 values between 4.96 and 5.774 values between 5.77 and 6.572 values between 6.57 and 7.373 values between 7.37 and 8.171 values between 8.17 and 8.981 values between 9.78 and 10.581 values between 10.58 and 11.392 values between 14.60 and 15.401 values between 17.00 and 17.811 values between 18.61 and 19.411 values between 22.62 and 23.421 values between 26.64 and 27.44offnegativepositiveoften

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. amount
  2. volume
  3. capita
  4. unit
  5. hours
  6. 体积
  7. 金额
  8. 小时
  9. amount
  10. units

Suppresses

  1. dings
  2. masters
  3. 四大
  4. 축
  5. _CONTINUE
  6. master
  7. rice
  8. ibName
  9. rir
  10. esub