Neuron Explorer

Qwen3-0.6B

lowercase 'l' starting a word

A neuron in layer 27 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 letter 'l' when it begins a new word or syllable, like 'lily', 'lathes' or 'lice'. It goes quiet or negative on capital letters such as 'L' in 'Lymphoma'. Turning it up made the text drift into repeated, garbled words, so the steering shows little about the neuron itself.

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

    66:108-110)⏎lo vinu, lə vinə “wine”⏎lo sale, rə ssalə, l

  2. #2 peak

    for it. For example, pressure will be needed when creating deep indents.⏎Lathes are divided into three types: the engine lathe, special purpose lathes and turret lathes. Some variants are placed on benches and others

  3. #3 peak

    9–1892) used both the one- and two-syllable pronunciations:⏎The purple flower droops; the golden bee⏎Is lily-cradled: I alone awake.⏎Both of these poets rhyme flower and

  4. #4 peak

    unciation: (-tru). [key]⏎1. Also,luster; esp. Brit.,lustre.a period of five years.⏎2. Rom. Hist.a lustration or ceremonial purification of the people, performed every five years, after the

  5. #5 peak

    professionals like lawyers and teachers. This undisciplined lot went on to brave bullets, were jailed, lathi-charged and suffered untold humiliations at the hands of the colonial rulers

  6. #6 peak

    advanced against Egypt by land and by sea. Ramses’ land army checked the enemy’s advance in southernmost Palestine, and the hostile ships were trapped after being lured into the waterways of the delta. Egypt averted conquest by the nor

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: Maybe you change the way you look you form more reactions you form reactions more reactions more reactions more reactions more reactions more reactions more reactions more reactions more reactions more reactions more reactions more reactions more reactions more reactions more reactions more reactions more reactions more reactions

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

    to regroup or to borrow with mixed numbers? Take a deep breath and let us take it one step at a time. Click and begin.⏎GCF and LCM by Prime Factorization⏎A straight forward way to find the greatest common factor

  2. #2 peak

    igations⏎Published: Sunday, September 28, 1919⏎Leave a Reply<|endoftext|>Combination Therapy May Help Patients With Follicular Lymphoma⏎A new study in The Journal of Experimental Medicine reveals

  3. #3 peak

    ideal treatment stage for Drinking Water, Wastewater and Water Reuse facilities.⏎UV light does not affect the taste,

  4. #4 peak

    environmental factors. Many Councils use an estimated useful life of somewhere between 8 and 25 years.⏎- Sealed Road⏎- Surface Treatment⏎- Wearing Surface⏎- Asphalt Overlay⏎- Sprayed Seal Useful Life Discussion⏎-

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. L23:1760 suppresses
  2. L22:2646 excites
  3. L20:417 excites
  4. L4:1978 excites
  5. L19:593 weakly excites
  6. L18:198 weakly suppresses
  7. L24:2164 weakly excites
  8. L20:151 weakly excites
  9. L17:134 weakly suppresses
  10. L21:252 weakly excites
  11. L18:365 weakly excites
  12. L16:95 weakly suppresses
  13. L24:105 weakly suppresses
  14. L17:1982 weakly excites
  15. L3:2052 weakly excites
  16. L9:476 weakly suppresses
  17. L26:495 weakly suppresses
  18. L22:766 weakly suppresses
  19. L20:52 weakly suppresses
  20. L0:94 weakly excites
  21. L22:1383 weakly excites
  22. L12:1815 weakly excites
  23. L19:2548 weakly excites
  24. L0:662 weakly suppresses

Feeds later layers

None: this is the last layer.

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 -66.19 and -63.411 values between -43.96 and -41.181 values between -41.18 and -38.411 values between -24.52 and -21.741 values between -10.63 and -7.852 values between -7.85 and -5.071 values between -5.07 and -2.293804 values between -2.29 and 0.4986 values between 0.49 and 3.273 values between 3.27 and 6.041 values between 6.04 and 8.823 values between 8.82 and 11.602 values between 11.60 and 14.381 values between 42.16 and 44.94offnegativepositiveoften

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. nice
  2. protected
  3. section
  4. uke
  5. ert
  6. thag
  7. etect
  8. curring
  9. works
  10. -widgets

Suppresses

  1. 意外
  2. дачи
  3. 日内
  4. Shib
  5. 糟糕
  6. Украины
  7. 不起
  8. 淋
  9. lez
  10. shy