Neuron Explorer

Qwen3-0.6B

unclear: energy, sunlight and rate words

A neuron in layer 9 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 responds to words about energy, sunshine and amounts of time or rate, such as 'sunlight', 'hours of sunshine' and 'energy consumption'. It is strongly negative on words like 'time' and 'at' in rate problems. The link is loose, and turning it up did not give a clear theme.

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

    the use of enzyme replacement therapy—however, this happened at an earlier age in male patients.⏎Having a

  2. #2 peak

    view PDF:⏎Energy community Nos Bambins explained⏎Consumers in an energy community buy energy at a lower rate from one or more producers through collective self-consumption. For this purpose, producers and consumers must be jointly represented by a legal

  3. #3 peak

    winter/early spring, for flowers.⏎Origin: Native to South Africa.⏎Cultivation: Grow Clivia miniata in bright light, but not in direct sun. Use well-draining soil and keep it on the dry side, watering the

  4. #4 peak

    To give you an idea of the difference between the weather in the UK and southern Europe. In the UK we have on average about 1000+ hours of sunshine per year, where as in southern Europe it's more like 2

  5. #5 peak

    aide.⏎*U.S. Department of Health and Human Services, December 1, 2015.⏎3. Doesn't Medicare pay for long-term care?⏎Many people mistakenly believe that Medicare

  6. #6 peak

    for particular product categories. ENERGY STAR has expanded to cover new homes, most of the buildings sector, residential heating and cooling equipment, major appliances, office equipment, lighting, consumer electronics, and more product areas.⏎If all consumers, businesses, and

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 get 100000000000000000000000000000000000000000000

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

    ?<|endoftext|>A particle is moving along the parabola 4y = (x + 2)^2 in such a way that its x-coordinate is increasing at a constant rate of 2 units per second. How fast is the particle's

  2. #2 peak

    energy can be of different forms: kinetic, magnetic, electric … etc⏎In any domain, the power is therefore expressed as a quantity of energy per unit of time. The international unit for the power is in Joules/second (J/s

  3. #3 peak

    take Bond A, issued by Company Alpha, as an example. It has the following data:⏎- Face value: $1,000⏎- Annual coupon rate: 5%⏎- Coupon Frequency: Annual⏎- Years to maturity:

  4. #4 peak

    .⏎How to calculate the bond price? The bond price formula⏎Bond price is calculated as the present value of the cash flow generated by the bond, namely the coupon payment throughout the life of the bond and the principal payment, or the balloon payment

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. L7:2819 suppresses
  2. L7:1649 excites
  3. L8:874 excites
  4. L7:500 suppresses
  5. L6:1137 suppresses
  6. L8:1835 suppresses
  7. L7:2156 suppresses
  8. L8:3 excites
  9. L8:377 suppresses
  10. L7:1549 suppresses
  11. L6:2465 weakly excites
  12. L7:951 weakly excites "in" right before a year
  13. L6:2580 weakly suppresses
  14. L8:1666 weakly excites
  15. L6:2461 weakly suppresses
  16. L7:869 weakly excites
  17. L8:2910 weakly suppresses
  18. L8:1880 weakly excites
  19. L7:1610 weakly suppresses
  20. L8:12 weakly excites
  21. L8:2294 weakly suppresses
  22. L8:2471 weakly excites
  23. L7:1332 weakly suppresses
  24. L5:1267 weakly suppresses

Feeds later layers

  1. L20:1199 suppresses
  2. L11:1679 suppresses
  3. L10:733 suppresses
  4. L19:1348 suppresses
  5. L10:986 suppresses
  6. L10:915 excites
  7. L22:2171 suppresses
  8. L17:1228 excites
  9. L20:1387 suppresses
  10. L11:834 excites
  11. L12:2224 excites
  12. L22:1063 suppresses
  13. L10:1321 suppresses
  14. L17:2346 suppresses
  15. L16:2226 suppresses
  16. L10:637 suppresses
  17. L10:1707 excites
  18. L14:700 suppresses
  19. L11:292 suppresses
  20. L12:2782 suppresses
  21. L10:1098 suppresses
  22. L10:1350 suppresses
  23. L10:1925 excites
  24. L17:1416 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.

1 values between -2.42 and -2.321 values between -2.23 and -2.131 values between -1.84 and -1.741 values between -1.55 and -1.452 values between -1.45 and -1.354 values between -1.35 and -1.261 values between -1.06 and -0.971 values between -0.97 and -0.875 values between -0.87 and -0.778 values between -0.77 and -0.686 values between -0.68 and -0.584 values between -0.58 and -0.4814 values between -0.48 and -0.3930 values between -0.39 and -0.2981 values between -0.29 and -0.19299 values between -0.19 and -0.09913 values between -0.09 and 0.001349 values between 0.00 and 0.10741 values between 0.10 and 0.20281 values between 0.20 and 0.29100 values between 0.29 and 0.3937 values between 0.39 and 0.4912 values between 0.49 and 0.596 values between 0.59 and 0.683 values between 0.68 and 0.781 values between 0.78 and 0.882 values between 0.97 and 1.071 values between 1.17 and 1.261 values between 1.26 and 1.362 values between 1.36 and 1.46offnegativepositiveoften

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. .IsSuccess
  2. ModelError
  3. edef
  4. JSGlobal
  5. 钤
  6. UObject
  7. eties
  8. 自卑
  9. 屐
  10. InitializeComponent

Suppresses

  1. continuously
  2. stream
  3. gesch
  4. streams
  5. steadily
  6. running
  7. 潺
  8. continual
  9. continually
  10. streams