Neuron Explorer

Qwen3-0.6B

the word 'same' before a noun

A neuron in layer 8 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 lights up on the word "same" when it is followed by a noun or phrase that points back to something already mentioned, such as "the same dish" or "the same period". When it was turned up, the model's text kept coming back to the word "same" and to comparisons between things.

Written by Claude from this neuron's activations and steering outputs. Confidence: high. 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

    consumption, Newgent said. Even though slow cookers are typically on for hours at a time, they will burn less energy than a traditional oven to prepare the same dish, such as a roast.⏎Look for ways to lessen the amount of time

  2. #2 peak

    we read and on what we read” - whether a book or journal, e-reader, phone or computer."⏎Other research has found declines in student comprehension when the same material is read on-screen instead of in

  3. #3 peak

    3-year period studied and can expect to live 79.2 years. Oklahomans, however, gained only 0.3 years over the same period, to 75.4. (For a table listing all the

  4. #4 peak

    prior to the advent of OCT, other imaging technologies were using ultrasound waves or MRI for imaging.⏎However, swept source OCT follows a little bit different mechanism for the same process. Unlike sound waves or MRI techniques, OCT uses light waves for imaging.

  5. #5 peak

    , less steam is produced because of a larger mass of water. A wide fog pattern of water passing through the same gases will produce an enormous amount of steam because of the greater surface-to-mass

  6. #6 peak

    ophen daily (> 500 mg) were 93 percent more likely to develop hypertension than those not taking the drugs, while younger women taking the same dosage were 99 percent more likely.⏎For ibuprofen, older women

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 have been thinking about lately, and I have been thinking about lately. So, [insert your name], [insert your name] [insert your name] [insert your names] [insert your names] [insert your names] [

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

    . Ratifying CEDAW committed us to ‘being a society that promotes policies, laws, organisations, structures and attitudes that ensure women are given the same rights as men’.⏎Sex Discrimination Act passed⏎Australia passed the Sex Discrimination Act

  2. #2 peak

    of literature on air pollution and its relationship to cardiovascular diseases. The resulting scientific statement, which appears in the current issue of Circulation: Journal of the American Heart Association, concludes that air pollution is a serious public health threat and contributes to the development

  3. #3 peak

    digit of the second number. Each partial result should be aligned with the corresponding digit. That means the last digit of the partial product must be in the same column as the digit of the second number. No product may begin with any additional zeros.

  4. #4 peak

    ) / membrane wall thickness⏎where D is the diffusion coefficient for the membrane material and is expressed in L2 / t.⏎Note: In gas release applications, mass is released from the tubing on a molecular basis and immediately dissolves in the groundwater

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. L7:1508 excites
  2. L4:2695 suppresses
  3. L6:1851 weakly excites
  4. L6:1454 weakly excites
  5. L3:1944 weakly suppresses
  6. L3:1942 weakly suppresses
  7. L7:1088 weakly suppresses
  8. L7:1199 weakly suppresses
  9. L4:2376 weakly excites
  10. L2:84 weakly excites
  11. L0:1369 weakly suppresses
  12. L0:2856 weakly suppresses
  13. L1:2389 weakly suppresses
  14. L1:591 weakly excites
  15. L6:2317 weakly excites
  16. L6:1461 weakly suppresses
  17. L3:1567 weakly excites
  18. L5:2317 weakly suppresses
  19. L6:1437 weakly suppresses
  20. L3:2372 weakly excites
  21. L7:2196 weakly excites
  22. L5:2659 weakly excites
  23. L6:323 weakly suppresses
  24. L6:2498 weakly suppresses

Feeds later layers

  1. L10:1152 excites
  2. L12:2717 excites
  3. L10:411 excites
  4. L13:2305 excites
  5. L11:1430 weakly excites
  6. L11:2712 weakly excites
  7. L12:2426 weakly excites
  8. L18:851 weakly excites
  9. L14:1302 weakly excites
  10. L18:2881 weakly excites
  11. L12:3057 weakly excites
  12. L16:755 weakly excites
  13. L15:1216 weakly excites
  14. L14:2783 weakly excites the word 'same' in 'the same'
  15. L10:2989 weakly excites
  16. L17:2038 weakly suppresses
  17. L9:2725 weakly excites
  18. L14:926 weakly suppresses
  19. L19:940 weakly excites
  20. L19:2233 weakly excites
  21. L15:2919 weakly excites
  22. L9:1950 weakly excites
  23. L12:2525 weakly excites
  24. L22:1510 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 -2.61 and -2.311 values between -2.02 and -1.721 values between -1.72 and -1.433 values between -1.43 and -1.133 values between -1.13 and -0.837 values between -0.83 and -0.54107 values between -0.54 and -0.242627 values between -0.24 and 0.051092 values between 0.05 and 0.3556 values between 0.35 and 0.656 values between 0.65 and 0.941 values between 2.13 and 2.421 values between 5.08 and 5.381 values between 6.56 and 6.861 values between 8.93 and 9.23offnegativepositiveoften

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. ё
  2. OUTH
  3. -pattern
  4. same
  5. Ot
  6. achen
  7. ழ
  8. enchmark
  9. unce
  10. orphism

Suppresses

  1. xFD
  2. ayar
  3. 就知道
  4. 资产负债
  5. 珙
  6. Seas
  7. ,默认
  8. 漫长的
  9. 非常多的
  10. gev