Neuron Explorer

Qwen3-0.6B

the word 'put'

A neuron in layer 19 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 responds to the word 'put' and its forms, as in 'help you put', 'put together' and 'put a lid on'. Pushing it up did not produce clearly put-related text; the outputs wandered across topics.

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

    bone density test called a DEXA, which looks for low bone density as a possible cause of the injury. A team of sports medicine experts can help you put shin splints behind you and keep running strong.⏎—Dr. Jordan Metzl

  2. #2 peak

    confusion.⏎Dividing with Decimals⏎Many times students freeze at the sight of a decimal, but there’s no need to do so. Let me help you put the decimal drama to rest.⏎Can

  3. #3 peak

    experiences and the people around her. My advice to you is stop worrying about whether your teen’s attitude measures up to other teens’ attitude but to encourage her to put her best attitude forward at all times.⏎Why? Because her attitude affects her behaviour

  4. #4 peak

    Ready to start? Let’s dive in!⏎A little history of the SSL certificate⏎They say “to know your future you must know your past”, right? Put into a closer, business perspective, I’d rephrase that with “to better

  5. #5 peak

    spokesperson, Tim Farron, enjoys a strong base of support in the<|endoftext|>Many of us are inclined not to talk about things that upset us. We try to put a lid on our feelings and hope that saying nothing will be for the best.

  6. #6 peak

    , windy days are one of the worst. Having spent plenty of days battling a headwind on a ‘get out for a spin’ type of ride, we put together a few basic tips which we use at AATR to help us through

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: some of the the world is not well, and some of the other the world is not well. the world is not well for the first, the second, and the last of the 1999, their share 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

    and immature Elizabeth Ann and follows her through a stunning metamorphosis into an independent and vibrant Betsy.⏎Fisher’s keen intelligence, delightful writing style, and perceptive nature shine through the pages of Understood Betsy. While the story was

  2. #2 peak

    tables, and not with any of the other⏎storage engines. Also, this warning against sharing a data⏎directory among servers always applies in an NFS environment.⏎Permitting multiple MySQL servers to access a common data⏎directory over NFS is a

  3. #3 peak

    powder that was invented by Hakaru Masumoto at Tohoku Imperial University in Sendai, Japan, about 1936 as an alternative to permalloy in inductor applications for

  4. #4 peak

    (more information)⏎©Copyright 1993 by the Regents of the University of California⏎AND IS MAINTAINED FOR ARCHIVAL PURPOSES ONLY⏎Perennial to trees, from membranous bulb, fibrous corm, sc

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. L17:214 excites
  2. L0:498 excites
  3. L6:875 suppresses
  4. L0:497 excites
  5. L2:1554 excites
  6. L18:103 suppresses
  7. L1:6 suppresses
  8. L18:196 suppresses
  9. L7:300 excites
  10. L10:237 excites
  11. L15:381 excites
  12. L15:129 suppresses
  13. L18:1380 excites
  14. L7:2731 weakly suppresses
  15. L18:133 weakly suppresses
  16. L18:1104 weakly excites
  17. L17:350 weakly suppresses
  18. L17:517 weakly suppresses "but" in "not only X, but" phrases
  19. L17:241 weakly excites
  20. L16:260 weakly excites
  21. L2:3071 weakly excites
  22. L18:139 weakly suppresses
  23. L16:989 weakly excites
  24. L18:322 weakly excites

Feeds later layers

  1. L21:518 suppresses
  2. L23:1398 weakly suppresses
  3. L21:2040 weakly suppresses
  4. L20:411 weakly suppresses
  5. L22:357 weakly excites
  6. L20:1908 weakly suppresses
  7. L20:283 weakly suppresses
  8. L24:782 weakly excites
  9. L20:1090 weakly suppresses
  10. L26:1255 weakly suppresses
  11. L27:155 weakly suppresses
  12. L20:648 weakly excites
  13. L23:670 weakly suppresses
  14. L26:2917 weakly suppresses
  15. L27:2928 weakly excites
  16. L20:2763 weakly excites
  17. L21:1264 weakly suppresses
  18. L21:2968 weakly suppresses
  19. L21:1188 weakly suppresses
  20. L24:2092 weakly excites "self" before esteem or image
  21. L25:199 weakly suppresses
  22. L24:1473 weakly excites
  23. L23:1206 weakly suppresses
  24. L24:1240 weakly 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 -21.52 and -20.741 values between -15.30 and -14.531 values between -10.64 and -9.861 values between -9.86 and -9.091 values between -7.53 and -6.763 values between -6.76 and -5.981 values between -5.98 and -5.202 values between -5.20 and -4.432 values between -4.43 and -3.654 values between -3.65 and -2.876 values between -2.87 and -2.1012 values between -2.10 and -1.32104 values between -1.32 and -0.543230 values between -0.54 and 0.23509 values between 0.23 and 1.0113 values between 1.01 and 1.795 values between 1.79 and 2.564 values between 2.56 and 3.341 values between 3.34 and 4.122 values between 4.12 and 4.893 values between 4.89 and 5.671 values between 5.67 and 6.451 values between 8.78 and 9.56offnegativepositiveoften

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. worm
  2. ал
  3. 拯
  4. piece
  5. marshal
  6. 层出
  7. /latest
  8. edition
  9. сли
  10. えて

Suppresses

  1. nails
  2. amer
  3. anced
  4. }}">{{$
  5. utable
  6. iciente
  7. cente
  8. ducation
  9. Specifications
  10. uated