Neuron Explorer

Qwen3-0.6B

"as" or "since" giving a reason

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 "as" (or "since") when it starts a clause that gives a reason, like "the test is hard to pass, as...". Turning it up did not produce a clear topic in the writing.

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

    , the maximum DSR typically allowed by lenders is around 60%.⏎For those individuals with irregular income, it may be harder to pass the stress test as

  2. #2 peak

    aka CLR. It do all the heart tasks of locating, loading and managing .NET types. This is a very important task to be done by the CLR, as it guarantees that the written types will function properly according to what

  3. #3 peak

    9% of the total population. This comes out to roughly 1.8 million Kurds living in Syria. This number, however, is anything but accurate as the Syrian government does not keep figures. Also the definition of ‘Kurd’

  4. #4 peak

    or as a takeout container from a fast food place⏎- egg cartons – either the styrofoam ones or cardboard ones (latter is preferable as you can plant these in the ground and they will rot away)⏎- plastic containers

  5. #5 peak

    inct pacing profiles result in similar perceptual responses and neuromuscular fatigue development⏎I found this study quite interesting as I've been investigating different pacing strategies. The authors wanted to understand "the effect

  6. #6 peak

    can be completely operated via the serial interface with a teletype. By the way, it is not possible to show the internal registers at the lamp registers, as it is possible at a processor built with the TTL technology.⏎Right beside the front

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 use of, or the display of, a screen, or a display device, or a display of a screen for the purposes of communication, or for the purposes of displaying visual information, or for the purposes of transmitting data, or for

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

    academic community use digital technologies to preserve the scholarly record and to advance research and teaching in sustainable ways ... Types of Sources for a Research Paper | Pen and the Pad There are two types of research<|endoftext|>The Apollo 11 space flight landed the first

  2. #2 peak

    , and a conclusion.⏎It is important that the consistency of the format be precise using the same paragraph spacing and font style/size throughout content of report. AgendaAn agenda informs the attendees, of what is going to happen during the meeting and help

  3. #3 peak

    concerns relating to privacy, ethics, and legality. The government has taken a recent active role in regulating online activity. Exploring Our Inner-self in Cyberspace Cyberspace is a new communication medium which enables us to understand our social behavior.

  4. #4 peak

    to understand how current works.⏎Current is the rate at which electrons flow past a point in a complete electrical circuit.⏎Want to Slash Your EMF Health Risks?⏎Good! Learn the one small change you should make right now.⏎To understand this

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. L8:1848 excites
  2. L8:200 suppresses
  3. L6:2621 suppresses
  4. L7:337 excites
  5. L8:573 excites
  6. L8:410 suppresses
  7. L8:911 suppresses
  8. L7:2570 excites
  9. L4:291 excites
  10. L8:361 excites
  11. L7:1197 excites
  12. L8:982 excites
  13. L4:175 suppresses
  14. L8:197 excites
  15. L6:250 excites
  16. L8:187 excites
  17. L7:2811 excites
  18. L3:487 suppresses
  19. L7:948 suppresses
  20. L6:2282 excites "and" after a contrast or pause
  21. L8:444 suppresses
  22. L8:3048 excites
  23. L8:441 excites 'or' linking alternatives
  24. L6:137 suppresses

Feeds later layers

  1. L13:345 excites
  2. L17:629 excites question mark after a rhetorical question
  3. L10:308 excites
  4. L10:144 excites
  5. L12:1405 excites
  6. L10:137 suppresses 'the' before a noun after 'of'
  7. L19:1072 excites
  8. L15:1543 excites
  9. L10:213 excites
  10. L17:2684 excites
  11. L13:346 excites
  12. L17:1567 excites
  13. L10:911 excites
  14. L14:1124 excites
  15. L14:2005 excites
  16. L17:839 excites
  17. L10:452 excites
  18. L17:72 suppresses
  19. L11:180 excites
  20. L11:25 suppresses
  21. L13:918 excites
  22. L13:1375 excites
  23. L19:282 suppresses
  24. L13:9 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.

2 values between -1.98 and -1.841 values between -1.84 and -1.701 values between -1.43 and -1.291 values between -1.29 and -1.152 values between -1.15 and -1.025 values between -1.02 and -0.8817 values between -0.88 and -0.7447 values between -0.74 and -0.61167 values between -0.61 and -0.47519 values between -0.47 and -0.331117 values between -0.33 and -0.201086 values between -0.20 and -0.06452 values between -0.06 and 0.08124 values between 0.08 and 0.2283 values between 0.22 and 0.3572 values between 0.35 and 0.4940 values between 0.49 and 0.6343 values between 0.63 and 0.7628 values between 0.76 and 0.9023 values between 0.90 and 1.049 values between 1.04 and 1.1712 values between 1.17 and 1.3113 values between 1.31 and 1.457 values between 1.45 and 1.597 values between 1.59 and 1.725 values between 1.72 and 1.864 values between 1.86 and 2.005 values between 2.00 and 2.131 values between 2.13 and 2.273 values between 2.27 and 2.412 values between 2.41 and 2.542 values between 2.54 and 2.681 values between 2.68 and 2.822 values between 2.82 and 2.951 values between 2.95 and 3.091 values between 3.09 and 3.231 values between 3.23 and 3.372 values between 3.37 and 3.50offnegativepositiveoften

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. asn
  2. (bin
  3. уй
  4. şim
  5. asn
  6. ному
  7. setQuery
  8. ERO
  9. itim
  10. 它可以

Suppresses

  1. into
  2. inely
  3. untreated
  4. 镑
  5. 除外
  6. estruct
  7. 小时前
  8. 真情
  9. ellen
  10. plaintext