Neuron Explorer

Qwen3-0.6B

the variable t for time

A neuron in layer 5 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 on the letter t when it stands for time in a formula, such as sin(ωt) or the t in t-tests. When turned up, the model's writing did not clearly change in a way tied to time, so the evidence is weak.

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

    ⏎t0=0; %set the initial time to zero⏎tend=1; %set the final time to 100⏎t

  2. #2 peak

    .m.⏎Inferential Statistics with SPSS⏎Using an SPSS data file, you'll test hypotheses with t-tests and regression analysis to predict risks and trends.⏎Tuesday, Oct. 1

  3. #3 peak

    power is then written as⏎Here the average of sin2 ωt over a cycle is 1/2 and that of sin ω t cos

  4. #4 peak

    it that way. That just means that I have to make sure that I use gravity as a negative number, since gravity always acts down.⏎vf = vi + at⏎= 56.3m/s + (-9.81m

  5. #5 peak

    is averaged over a complete cycle.⏎The alternating voltage and alternating current in the series RLC circuit at an instant are given by⏎v=Vm sin ωt and i = I m sin( ω t + φ)⏎where ϕ

  6. #6 peak

    the commands you give and the M-file are somewhat disparate. The process is illustrated using a single, simple differential equation:⏎Integrate this equation from t = 0 to t = 1. The exact solution can be found by

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: To get the most out of the product, the company's current capacity to process it, the company is currently looking for a profit, the company is trying to find a path to the next level, the next level requires a lot of work

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

    . Four state agencies committed up to $2.4 million to this facility, which is expected to reduce carbon dioxide emissions by 30,000 tons per year.⏎“We are proud to recognize Landfill Methane Outreach Program partners who

  2. #2 peak

    partner and is working towards greener solutions for utility demands. Each year, Seattle’s stormwater carries more than 8,200 tons of toxic metals and volatile chemicals into the city’s waterways. In addition,

  3. #3 peak

    energy resource prevents greenhouse gas 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

  4. #4 peak

    dangerous"!⏎When you are interviewing potential hvac contractors, you will hear phrases such as total cooling capacity, sensible and latent capacity, btu, and tonnage.⏎The Air Conditioning Contractors of America (ACCA) have a consumer area

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. L4:613 excites
  2. L2:1585 weakly excites
  3. L0:2925 weakly suppresses
  4. L4:3047 weakly excites
  5. L2:493 weakly suppresses
  6. L0:632 weakly suppresses
  7. L4:2089 weakly suppresses
  8. L0:2812 weakly suppresses
  9. L3:343 weakly suppresses
  10. L4:876 weakly suppresses
  11. L4:977 weakly excites
  12. L2:1399 weakly excites
  13. L0:246 weakly excites
  14. L2:2406 weakly suppresses
  15. L3:1319 weakly excites
  16. L3:2665 weakly suppresses
  17. L2:2749 weakly excites
  18. L3:2873 weakly excites
  19. L3:1723 weakly excites
  20. L2:1155 weakly excites
  21. L4:958 weakly suppresses
  22. L4:916 weakly suppresses
  23. L2:2923 weakly suppresses
  24. L4:2003 weakly excites

Feeds later layers

  1. L7:451 excites
  2. L22:1074 excites
  3. L9:383 excites
  4. L16:583 excites
  5. L20:1335 excites
  6. L25:565 excites
  7. L10:637 excites
  8. L14:1088 excites
  9. L12:2853 weakly excites
  10. L26:2065 weakly excites
  11. L12:2338 weakly excites
  12. L19:1929 weakly excites timestamps and dates in text
  13. L19:2242 weakly excites
  14. L8:1257 weakly excites
  15. L22:2601 weakly excites
  16. L26:1324 weakly excites
  17. L8:233 weakly excites
  18. L9:2117 weakly suppresses
  19. L8:488 weakly excites
  20. L10:456 weakly excites
  21. L19:1937 weakly suppresses
  22. L10:2050 weakly suppresses
  23. L19:1390 weakly suppresses
  24. L22:2445 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 -3.82 and -3.701 values between -1.54 and -1.421 values between -1.42 and -1.292 values between -0.91 and -0.783 values between -0.78 and -0.665 values between -0.66 and -0.532 values between -0.53 and -0.4046 values between -0.40 and -0.28252 values between -0.28 and -0.151077 values between -0.15 and -0.021812 values between -0.02 and 0.11568 values between 0.11 and 0.23106 values between 0.23 and 0.3621 values between 0.36 and 0.495 values between 0.49 and 0.611 values between 0.61 and 0.741 values between 0.74 and 0.872 values between 0.87 and 0.992 values between 1.12 and 1.25offnegativepositiveoften

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. 时间
  2. time
  3. 一天
  4. 时间和
  5. Ờ
  6. 时间段
  7. поя
  8. (time
  9. TIM
  10. coh

Suppresses

  1. APTER
  2. metis
  3. abet
  4. ave
  5. .setLevel
  6. itary
  7. .amazonaws
  8. deaux
  9. aceutical
  10. 尽