Neuron Explorer

Qwen3-0.6B

'ago' after a span of years

A neuron in layer 3 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 'ago' when it comes after a length of time, as in '66 million years ago'. Its negative side is on the word 'chain'. Turning it up did not bring out the time theme in the replies.

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

    66 million years ago - best-known for the extinction of the dinosaurs, the Cretaceous-Pale

  2. #2 peak

    families, educators, and other professionals.<|endoftext|>Tracking a Jurassic reversal of the Earth's magnetic field⏎Roughly 180 million years ago, during the height of the Jurassic period, the Earth's magnetic field flipped,

  3. #3 peak

    eylon-Tamils" who started coming from South-India over 1000 years ago and the "Plantation-Tamils" whose ancestors were brought by the British

  4. #4 peak

    has led to its popular moniker, the Cigar Galaxy. M82's burst of star formation was likely triggered a mere 100 million years ago in the latest of a series of bouts with another large galaxy, M81

  5. #5 peak

    quer table greeting us at the top of the⏎steps. Adorning each of the vessels are the origami butterflies, both⏎male and female.⏎Several years ago I⏎wrote a Shinto scholar who teaches at a major American university.

  6. #6 peak

    moved. The speed record is held by India, which started to make its way from East Gondwana to Eurasia about 140 million years ago at a speed of 20 centimeters per year.⏎Drilling into the

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: the lack of a proper government of fire, the lack of a proper chain of trust, and the financial misfeasance of control, which is the chain of events, and so on. It's a, a Japanese company, and a

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

    endless chain is run, forming two hanging loops. In one loop is placed a movable block, whose pulley is shaped to take the chain. The load is attached to the movable block and is raised by pulling on the

  2. #2 peak

    the potential for chemicals to leach from the plastic into the contents of the bottle. PET is a type of polymer, which means it is made up of long chains of molecules called monomers. These monomers can be linked together in different ways

  3. #3 peak

    should regain consciousness.''⏎The message says that doing this somehow relieves blood pressure and eases symptoms.⏎Like most medical advice dispensed in the form of a chain e-mail message, it has no scientific basis. In fact, following its advice

  4. #4 peak

    of two pulleys of different radii connected and rotating as one on a common axle. The pulleys have their circumferences grooved and spiked so that a chain will run in them without slipping. Over the pulleys an

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. L1:1 suppresses
  2. L2:2732 weakly excites
  3. L2:75 weakly suppresses
  4. L0:1088 weakly suppresses
  5. L1:2801 weakly excites
  6. L0:1301 weakly suppresses
  7. L2:2328 weakly suppresses
  8. L2:3038 weakly excites
  9. L2:2962 weakly suppresses
  10. L2:1468 weakly excites "over" in "take over"
  11. L1:1857 weakly suppresses
  12. L0:178 weakly suppresses
  13. L2:1036 weakly excites
  14. L0:1224 weakly suppresses
  15. L2:2711 weakly suppresses
  16. L2:2583 weakly suppresses
  17. L2:2102 weakly suppresses
  18. L0:2337 weakly suppresses
  19. L2:1899 weakly excites
  20. L2:2049 weakly suppresses
  21. L1:951 weakly excites
  22. L2:493 weakly suppresses
  23. L0:1774 weakly suppresses
  24. L1:2467 weakly suppresses

Feeds later layers

  1. L11:701 suppresses
  2. L4:1720 suppresses
  3. L19:3004 weakly suppresses
  4. L22:2356 weakly suppresses
  5. L24:2181 weakly suppresses
  6. L9:2141 weakly suppresses
  7. L27:1976 weakly suppresses
  8. L15:640 weakly excites
  9. L5:1743 weakly suppresses
  10. L10:616 weakly excites
  11. L8:2531 weakly suppresses
  12. L10:1343 weakly suppresses
  13. L12:824 weakly suppresses
  14. L9:690 weakly suppresses
  15. L12:2365 weakly suppresses
  16. L26:1578 weakly suppresses
  17. L7:1596 weakly excites
  18. L5:783 weakly suppresses
  19. L15:1427 weakly suppresses
  20. L12:1951 weakly excites
  21. L24:1542 weakly suppresses
  22. L12:1147 weakly suppresses
  23. L5:793 weakly excites
  24. L11:2873 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 -1.82 and -1.751 values between -1.41 and -1.341 values between -0.46 and -0.406 values between -0.40 and -0.3320 values between -0.33 and -0.2662 values between -0.26 and -0.19156 values between -0.19 and -0.12454 values between -0.12 and -0.061238 values between -0.06 and 0.011035 values between 0.01 and 0.08575 values between 0.08 and 0.15204 values between 0.15 and 0.22105 values between 0.22 and 0.2835 values between 0.28 and 0.3513 values between 0.35 and 0.421 values between 0.49 and 0.551 values between 0.83 and 0.89offnegativepositiveoften

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. ated
  2. HEMA
  3. olum
  4. ician
  5. -plane
  6. ATED
  7. phia
  8. lectual
  9. сад
  10. elaide

Suppresses

  1. Lorem
  2. 长长的
  3. producción
  4. production
  5. baj
  6. production
  7. produção
  8. ök
  9. ��
  10. Production