Neuron Explorer

Qwen3-0.6B

the digit 1 in numbers

A neuron in layer 11 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 responds to the number 1 (and sometimes zeros) inside numbers, formulas, and maths problems. Turning it up made the model's text wander into unrelated topics rather than numbers.

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

    6 inches. This radium emits tiny amounts of radon into the atmosphere. On average, one part of radon is present in 1 x 1021 part of air.Radon is also present in some spring waters,

  2. #2 peak

    areas of mainland China. In 1955, a re-evaluation took place and a new Yuan Renminbi was introduced at a rate of 1 new Yuan to 10,000 old Yuan.⏎The Renmin

  3. #3 peak

    energy is expected to be saved over ten years when using a solar water heater compared to the electricity consumption of an equivalent electric water heater. 1 x STC is 1 x MWh of electricity saved over 10 years = 1

  4. #4 peak

    know how to solve that. We can multiply by 5 and divide by 5.⏎- 1/5 times 5 is just going to be 1. So we haven't changed the value of the expression.⏎- But when we

  5. #5 peak

    of all, it is important to clarify what exactly a percentage is, and this is nothing more than a quantity or number that represents a fraction of the number 100.⏎In other words, it is a part of a general number that

  6. #6 peak

    as the true power of the circuit.⏎(i) For a purely resistive circuit, the phase angle between voltage and current is zero and cos ϕ = 1.⏎∴ Pav = VRMS IRMS⏎(ii) For a purely inductive

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 think it's possible to get a 12.5. Let me check... Let me get it right... Okay, 12.5, 12.5. Let me get it right... Okay, 1

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

    and attractive indoor environments. It is no surprise that this sustainable building boom has also led to the construction of more efficient schools. Studies show that net-zero K-12 schools consume

  2. #2 peak

    or uncertain? "Fluctuations in labor input in a RBC model, not caused by real wage fluctuations, should be negatively correlated with consumption."⏎Choose 1 out of the following 2. Provide a strict formal argument. Worth 2

  3. #3 peak

    10 log10(MAX^2/MSE) = 10 log10(MAX/(MSE)^(1/2))^2 =

  4. #4 peak

    . As the first black woman we have ever seen in the Tunisian Parliament, I am proud to be part of that minority, always.”⏎Ks<|endoftext|>Select one (1) column from a dataset with whole non-negative integers. A good dataset

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. L10:848 suppresses
  2. L9:1373 suppresses
  3. L10:1284 excites
  4. L10:1602 excites the number 1 as a unit value
  5. L6:902 excites
  6. L4:961 excites
  7. L7:753 excites
  8. L5:559 suppresses
  9. L10:2192 suppresses
  10. L3:244 suppresses
  11. L9:977 suppresses the last digit of a decade year
  12. L8:972 excites
  13. L10:773 weakly excites
  14. L2:1225 weakly suppresses
  15. L9:2714 weakly excites
  16. L6:18 weakly excites
  17. L10:722 weakly suppresses
  18. L10:548 weakly excites zeros inside large numbers
  19. L7:39 weakly excites
  20. L1:2025 weakly excites
  21. L5:920 weakly excites
  22. L7:2305 weakly suppresses
  23. L5:91 weakly excites
  24. L2:1462 weakly suppresses "factors" after "other" or "several"

Feeds later layers

  1. L13:791 excites
  2. L13:667 excites zeros inside decimal numbers
  3. L12:641 suppresses
  4. L16:950 excites
  5. L16:1012 excites 'one' before 'of' in 'is one of the'
  6. L18:2221 excites
  7. L13:919 excites
  8. L13:2411 excites
  9. L15:2061 excites
  10. L18:726 suppresses
  11. L14:1170 excites
  12. L13:2568 suppresses
  13. L13:564 suppresses
  14. L14:1414 excites
  15. L12:2435 weakly excites
  16. L12:370 weakly suppresses
  17. L15:2651 weakly excites
  18. L18:2793 weakly excites
  19. L13:2485 weakly excites
  20. L12:1615 weakly excites
  21. L16:1420 weakly suppresses
  22. L14:2062 weakly excites
  23. L16:2576 weakly suppresses
  24. L16:1856 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 -2.03 and -1.901 values between -1.02 and -0.902 values between -0.77 and -0.645 values between -0.64 and -0.5233 values between -0.52 and -0.39161 values between -0.39 and -0.27626 values between -0.27 and -0.141602 values between -0.14 and -0.021207 values between -0.02 and 0.11227 values between 0.11 and 0.2427 values between 0.24 and 0.366 values between 0.36 and 0.492 values between 0.49 and 0.612 values between 0.61 and 0.741 values between 0.74 and 0.861 values between 1.24 and 1.371 values between 1.37 and 1.491 values between 1.62 and 1.741 values between 2.37 and 2.501 values between 2.87 and 3.00offnegativepositiveoften

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. ESIS
  2. .setCharacter
  3. ease
  4. .CompareTo
  5. ['',
  6. զ
  7. üğü
  8. 日起
  9. devez
  10. WITHOUT

Suppresses

  1. ajo
  2. intr
  3. ecure
  4. repid
  5. ensive
  6. ressive
  7. Peninsula
  8. ench
  9. ids
  10. パー�