Neuron Explorer

Qwen3-0.6B

'is' or '1' after a variable

A neuron in layer 8 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 fires on a short word or symbol that names or sits right after a variable, such as "A is" in a formula, "s1" in code, or "described" and "above" when pointing back to something said earlier. Its steering effects were unrelated to these cases, so the pattern is mixed.

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

    supercoiled, linear and open form of DNA?⏎The equation for calculating extinction coefficients is stated by Beer's Law:⏎A = epsilon.c.l⏎Where A is the absorbance measurement at a given wavelength⏎epsilon is the extinction coefficient in M

  2. #2 peak

    . It is one of over a hundred billion or so such stars inside our cosmic system, unremarkable aside from its status as our nearby neighbor. Circling Proxima is an intriguing yet puzzling world, called Proxmia b, found

  3. #3 peak

    . President Andrew Johnson. He was a colorful and often controversial figure on the national stage and in the Massachusetts political scene, during his one term as Governor.⏎Butler, a successful trial lawyer, served in the Massachusetts legislature as an antiwar Democrat

  4. #4 peak

    are two quanties that are in the same units of measure. The decibel is 0.1 bel, so the decibel value LdB is LdB = 10 log10 (P1/P0).⏎Define the mean

  5. #5 peak

    = 'Hello, this is Tom's laptop' >>> Output: >>> s1 = 'Hello, this is Tom's laptop' File "", line 1 s1 = 'Hello, this is Tom's laptop'⏎```The above code would give

  6. #6 peak

    ,- 1) are orthogonal vectors in R 4 . Write the vector X = (1 , 1 , 1 , 2) in the form X = a U +<|endoftext|>Hepatitis B vaccine⏎The hepatitis B vaccine (

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: “If I was in a situation where I have to be a leader, but it’s not just a matter of getting more things to do, but being a bit more...” I think that maybe I just have to try to think of

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

    Only this way can the current and previous layers chemically bond and become a single solid object.⏎This phenomenon is known as overcuring. For the reasons just described, this overcuring is necessary and cannot be completely avoided.⏎However, over

  2. #2 peak

    using words effectively. The essay must be well researched and combine and analyze different sources and data. All these facilitate clear writing. An essay must have the qualities mentioned above. Additionally, it must be well-organized and formatted. The writing skills acquired

  3. #3 peak

    leads to reduced efficiency of the diesel engine itself, at the same time creates a remarkable potential for increased power output on both power turbines and steam turbines. The above mentioned potential compensates the reduction of diesel engine efficiency with surplus.⏎Accordingly, the

  4. #4 peak

    and alcohol consumption. Some people may snore every night, while others snore only occasionally.⏎What is sleep apnea?⏎Sleep apnea is similar to snoring, except that the airway becomes completely constricted. As a result, it

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. L6:1040 excites
  2. L7:332 suppresses
  3. L7:352 excites
  4. L7:460 suppresses
  5. L7:269 excites
  6. L5:523 excites
  7. L5:904 excites
  8. L4:443 suppresses
  9. L6:484 excites
  10. L5:372 suppresses
  11. L6:116 excites
  12. L7:380 excites
  13. L7:1320 weakly excites
  14. L3:151 weakly suppresses
  15. L7:1521 weakly excites
  16. L6:277 weakly suppresses
  17. L7:99 weakly suppresses
  18. L7:1285 weakly suppresses
  19. L7:2514 weakly suppresses
  20. L7:1218 weakly excites
  21. L6:910 weakly suppresses
  22. L6:39 weakly suppresses
  23. L7:301 weakly suppresses
  24. L6:1102 weakly excites

Feeds later layers

  1. L10:1135 suppresses
  2. L10:581 suppresses
  3. L9:2458 suppresses
  4. L9:342 suppresses
  5. L12:590 excites
  6. L9:864 suppresses
  7. L11:2305 suppresses
  8. L11:1604 weakly suppresses
  9. L9:1368 weakly suppresses
  10. L13:2760 weakly suppresses
  11. L14:2912 weakly excites
  12. L16:3014 weakly excites
  13. L17:2094 weakly excites
  14. L14:1511 weakly suppresses
  15. L12:2515 weakly suppresses
  16. L15:1687 weakly excites
  17. L10:1973 weakly suppresses
  18. L14:2848 weakly suppresses
  19. L10:261 weakly suppresses
  20. L15:178 weakly suppresses
  21. L10:1735 weakly suppresses
  22. L23:1088 weakly excites
  23. L9:2738 weakly excites
  24. L11:2655 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 -1.03 and -0.982 values between -0.60 and -0.543 values between -0.54 and -0.495 values between -0.49 and -0.4314 values between -0.43 and -0.3828 values between -0.38 and -0.3275 values between -0.32 and -0.27119 values between -0.27 and -0.21250 values between -0.21 and -0.16404 values between -0.16 and -0.10591 values between -0.10 and -0.05994 values between -0.05 and 0.01719 values between 0.01 and 0.06311 values between 0.06 and 0.11185 values between 0.11 and 0.1794 values between 0.17 and 0.2245 values between 0.22 and 0.2825 values between 0.28 and 0.3312 values between 0.33 and 0.3911 values between 0.39 and 0.446 values between 0.44 and 0.503 values between 0.50 and 0.552 values between 0.55 and 0.611 values between 0.61 and 0.662 values between 0.66 and 0.721 values between 0.72 and 0.771 values between 0.77 and 0.831 values between 0.88 and 0.931 values between 0.99 and 1.041 values between 1.04 and 1.101 values between 1.10 and 1.15offnegativepositiveoften

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. )&&(
  2. стве
  3. .SwingConstants
  4. )||
  5. )||(
  6. สเต
  7. Onc
  8. avo
  9. ительно
  10. itur

Suppresses

  1. izen
  2. .places
  3. 床上
  4. 灰尘
  5. testData
  6. _bullet
  7. ��
  8. shale
  9. '//
  10. 愿