Neuron Explorer

Qwen3-0.6B

decimal point inside a number

A neuron in layer 24 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 dot in decimal numbers like '29.5 days' or '0.25V'. Turning it up gave random, scrambled text, so the steering does not show a clear theme beyond the snippets.

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

    28 days and a lunar cycle lasting 29.5 days.⏎In addition, folklore often suggests that women are more likely to be

  2. #2 peak

    please remember to carry a converter!⏎Precaution 2: Choosing a power bank⏎So far, the standard voltage of USB is 5V±0.25V. However, the output voltage of some power banks on the market

  3. #3 peak

    best performance in delay time, area, and power product results. A 64-bit carry-look-ahead adder with RALA is fabricated by 0.25-mum CMOS technology to verify its feasibility and functionality. The area

  4. #4 peak

    regularity improves at each step).⏎The big-picture takeaway from TSMC’s announcement is that while double patterning is already in<|endoftext|>- Размер: 2.3 Mегабайта⏎- Количество слайдов: 1

  5. #5 peak

    well as Ataluren pontent inhibitor an summary of the Ataluren pontent inhibitor pathways/proteins that are activated in response to each type of damage. A. A double strand break DNA break (DSB) most often results in

  6. #6 peak

    <|endoftext|>Originally intended for use as a video connector in radar applications, UHF coaxial connectors are general purpose units developed for use in low frequency systems from 0.6 – 300 MHz Invented for use in the radio industry in

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: we can get a lot of information from the we of the we we we we we we we we we we we we we we we we we we we we we we we we we we we we we we we we we we we we

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

    reach out to Neuro-Behavioral Clinical Research for help and information on anxiety.⏎RECEIVE A $75 BONUS⏎WHEN YOU REFER A FRIEND!<|endoftext|>- About CSAIL⏎- News + Events⏎- Alumni & Friends

  2. #2 peak

    toured South India extensively and composed songs on the various deities of the religious pantheon. He had met both Tyāgarāja and Śyām<|endoftext|>Different cultures have been using psychedelic substances in rituals for thousands of years. In many

  3. #3 peak

    can safely remove.⏎But remember that you should never cut off more than two-thirds of a root at any time.⏎Also,<|endoftext|>Title VII makes sexual discrimination, i.e., using gender as a reason for making

  4. #4 peak

    acclaimed literary biographer of Kurt Vonnegut and Harper Lee comes the life story of a song, one of the most iconic ever written: John Lennon's "Imagine".⏎"Twenty-two lines of graceful, plain-spoken faith in the power

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. L23:509 strongly suppresses
  2. L23:179 strongly excites
  3. L23:561 strongly excites
  4. L22:67 strongly suppresses
  5. L21:524 strongly suppresses
  6. L22:597 strongly suppresses end of document token
  7. L22:3045 strongly suppresses
  8. L22:820 suppresses
  9. L19:1197 suppresses
  10. L20:473 suppresses
  11. L18:382 suppresses
  12. L22:376 excites
  13. L18:227 suppresses
  14. L18:1808 suppresses
  15. L16:432 suppresses period after month or initial
  16. L15:403 suppresses period inside an abbreviation
  17. L19:68 excites full stops closing a claim
  18. L19:344 excites periods ending explanations
  19. L19:3015 excites
  20. L17:347 excites full stops ending informative sentences
  21. L22:430 suppresses
  22. L16:762 excites
  23. L9:16 suppresses unclear: periods inside numbers and names
  24. L15:184 suppresses

Feeds later layers

  1. L27:446 strongly excites
  2. L26:1200 strongly excites
  3. L27:1637 strongly excites
  4. L27:137 strongly excites
  5. L27:1588 excites
  6. L27:248 excites
  7. L26:114 excites
  8. L26:517 excites
  9. L27:479 excites
  10. L27:647 excites
  11. L27:508 excites
  12. L27:59 excites full stops in running text
  13. L26:450 excites
  14. L26:773 excites
  15. L26:157 suppresses
  16. L27:94 excites
  17. L27:854 excites
  18. L26:778 excites capital letters inside acronyms
  19. L27:452 excites
  20. L26:630 suppresses
  21. L27:123 excites
  22. L26:372 excites
  23. L26:27 suppresses
  24. L27:228 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.

3 values between -15.34 and -14.412 values between -11.60 and -10.664 values between -9.72 and -8.783 values between -8.78 and -7.857 values between -7.85 and -6.912 values between -6.91 and -5.979 values between -5.97 and -5.049 values between -5.04 and -4.1012 values between -4.10 and -3.168 values between -3.16 and -2.2261 values between -2.22 and -1.291180 values between -1.29 and -0.352118 values between -0.35 and 0.59262 values between 0.59 and 1.5296 values between 1.52 and 2.4645 values between 2.46 and 3.4026 values between 3.40 and 4.3422 values between 4.34 and 5.279 values between 5.27 and 6.216 values between 6.21 and 7.153 values between 7.15 and 8.085 values between 8.08 and 9.025 values between 9.02 and 9.962 values between 9.96 and 10.904 values between 10.90 and 11.832 values between 11.83 and 12.771 values between 12.77 and 13.711 values between 13.71 and 14.641 values between 21.20 and 22.14offnegativepositiveoften

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. The
  2. That
  3. However
  4. This
  5. Then
  6. The
  7. →If
  8. →The
  9. There
  10. These

Suppresses

  1. 的方向
  2. 已久
  3. 月以来
  4. alytics
  5. eness
  6. 的身影
  7. matter
  8. utta
  9. �能
  10. 好