Neuron Explorer

Qwen3-0.6B

'each' in 'each other'

A neuron in layer 9 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 word 'each' when it is followed by 'other', as in 'with each other' or 'against each other'. Turning it up did not produce a clear theme in the written text.

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

    too thin, it will not dissipate heat correctly and be more prone to warping.⏎The brake rotor consists of two braking contact surfaces that must be parallel with each other, or else the brakes will pulsate when they are applied. In order

  2. #2 peak

    drop will equal the sum of the voltage drops measured across each resistor separately. This tells you that both the resistors' voltage drop waveforms are in-phase with each other, since they add simply and directly.⏎Measure voltage dropped across both capacitors

  3. #3 peak

    eventually stopped but only because Romeo and Juliet died. This was mainly because of the Friar.⏎The Capulets and Montagues were not on good terms with each other. Unfortunately though, Romeo and Juliet fell in love with each other regardless if

  4. #4 peak

    ix more than a few pages of paper to your fridge.⏎To see this for yourself, stick two fridge magnets together, back to back. They will slide against each other in one direction. If you slide them at right angles to that, they

  5. #5 peak

    .⏎Find the area of the shaded region created by the two overlapping⏎triangles in terms of a and b?⏎Position the lines so that they are perpendicular to each other.⏎What can you say about the equations of perpendicular lines?⏎ABCD is

  6. #6 peak

    ⏎meant for such use. Another risk with NFS is that you must⏎devise a way to ensure that two or more servers do not interfere⏎with each other. Usually NFS file locking is handled by the⏎lockd daemon, but

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 blank Friday 19th, 2023 January 1, 2016 This is an error type of the unknown type of the unknown type of the unknown type of the "general" type of the

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

    631–642, 2013. My thoughts precipitated a brief conversation with Erella Hovers in which, for the umpteenth time, she expounded the theory that a fossil

  2. #2 peak

    0 us, https://commons.wikimedia.org/w/index.php?curid=12708190<|endoftext|>

  3. #3 peak

    structure = function.⏎(Image from: https://commons.wikimedia.org/w/index.php?curid=1267900)⏎Want

  4. #4 peak

    08 — but declined to say which types of arms — several lower courts have had their say on whether Americans can own machine guns.⏎The U.S. courts of appeals for the Third,

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. L6:1299 strongly suppresses
  2. L8:2074 strongly excites
  3. L7:663 strongly suppresses
  4. L6:2016 strongly excites
  5. L6:1463 strongly excites
  6. L6:2146 excites
  7. L6:809 suppresses
  8. L8:852 suppresses comma inside large numbers
  9. L8:448 excites
  10. L7:2026 excites
  11. L8:2858 excites
  12. L6:1695 excites
  13. L8:2388 suppresses
  14. L3:1661 suppresses
  15. L6:2069 excites
  16. L4:1891 suppresses
  17. L7:3055 suppresses
  18. L6:1122 suppresses
  19. L7:2370 suppresses
  20. L5:2136 excites
  21. L8:2375 excites
  22. L5:1387 excites
  23. L8:2078 excites
  24. L7:2878 excites

Feeds later layers

  1. L16:592 strongly excites
  2. L10:346 strongly excites "each" in "each other" phrases
  3. L10:152 strongly excites
  4. L11:173 excites
  5. L18:708 excites
  6. L17:259 excites
  7. L16:415 excites
  8. L15:1616 suppresses word fragments mid-word
  9. L18:322 suppresses
  10. L11:300 excites
  11. L18:828 excites
  12. L15:1900 suppresses
  13. L15:646 excites
  14. L19:395 excites
  15. L14:713 excites
  16. L14:611 excites
  17. L11:1384 excites
  18. L18:564 excites
  19. L20:3066 excites
  20. L10:42 excites
  21. L19:1204 excites
  22. L19:107 suppresses
  23. L20:486 excites
  24. L17:446 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 -1.97 and -1.781 values between -1.78 and -1.591 values between -1.59 and -1.395 values between -1.39 and -1.205 values between -1.20 and -1.014 values between -1.01 and -0.824 values between -0.82 and -0.6234 values between -0.62 and -0.43268 values between -0.43 and -0.241296 values between -0.24 and -0.041817 values between -0.04 and 0.15317 values between 0.15 and 0.3464 values between 0.34 and 0.5424 values between 0.54 and 0.7323 values between 0.73 and 0.9213 values between 0.92 and 1.117 values between 1.11 and 1.315 values between 1.31 and 1.502 values between 1.50 and 1.693 values between 1.69 and 1.891 values between 1.89 and 2.081 values between 2.08 and 2.271 values between 2.27 and 2.462 values between 2.46 and 2.663 values between 2.66 and 2.851 values between 2.85 and 3.041 values between 3.43 and 3.621 values between 3.62 and 3.811 values between 4.78 and 4.972 values between 5.55 and 5.74offnegativepositiveoften

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. 치
  2. ственно
  3. imately
  4. ับ
  5. ้า
  6. 得
  7. 冲
  8. ầy
  9. и
  10. ンド

Suppresses

  1. 他们都
  2. .raise
  3. nees
  4. atsby
  5. noop
  6. leshoot
  7. ()?;⏎
  8. "})
  9. iddles
  10. icerca