Neuron Explorer

Qwen3-0.6B

"etc" closing a list

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 lights up on the word "etc" at the end of a list of examples, such as "bread, rice, grains... etc." When it was turned up, the model's writing mostly fell into repetitive loops, so the effect on the text is not clear.

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

    approach to crude oil causation is, the operating expenses tend to increase due to more spending on transportation and indirect expenses like employee travel allowance, third party fleet charges etc. This reduces corporate earnings. The reverse should be true

  2. #2 peak

    apples are good for heart patients. It and keeps the digestive track balanced. The nutritional composition of apples is very rich in vitamins, minerals, carbohydrates and amino acids etc. Apples are also very good source of vitamin B-Complex.⏎Apple contains

  3. #3 peak

    reflects our crisis with growing racism and intolerance. Clearly, discrimination against different groups in Egypt is not uncommon whether it was based on gender, religious beliefs, class, etc. Activist Fatma Emam recently wrote an article of her experience as a

  4. #4 peak

    race of Kurooshdusha – some of famous persons of this race are Sacepenthu, Seyaamagan, Vetharppan etc., Vetharppan’s third son belonged to the Saethe race,

  5. #5 peak

    as the name of a mountain ridge. The name is derived from a postulated basic meaning “throat, neck,” which Christian Bartholomae translated as neck etc. of daevic beings (see DĒW), and mentioned manao

  6. #6 peak

    cotton is a popular choice and its demand is increasing.⏎Organic cotton is used in several products such as cotton swabs, baby diapers, towels, sheets, etc. Hemp has high durability and requires less water. Organic hemp is used in paper

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 most effective. That is to say, the most effective. The most effective. That is to say. The most effective. I have not had much. I have not made much. I have not made much. I have not made

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 chemical requirements for specific purposes."— Presentation transcript:⏎Types of Portland Cement Different types of portland cement are manufactured to meet various physical and chemical requirements for specific purposes. Portlant cements are manufactured to meet the specifications of ASTM C1

  2. #2 peak

    is another paragraph, with a sentence that is split over several lines.Will get formatted as:⏎This is another paragraph, with a sentence that is split over several lines.<|endoftext|>Insufficient vocabulary, comprehension and literacy skills negatively impact children for the rest

  3. #3 peak

    CD prevalence, their risk factors, and treatments.⏎Copyright © 2020 The Royal Society for Public Health. Published by Elsevier Ltd. All rights reserved.<|endoftext|>We all grew up hearing the phrase, “Good night, sleep tight

  4. #4 peak

    ⏎- 1st Photos of Mars by Curiosity Rover (Gallery)⏎Copyright 2012 SPACE.com, a TechMediaNetwork company. All rights reserved. This material may not

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. L18:1437 strongly suppresses
  2. L18:1471 suppresses
  3. L18:2155 suppresses
  4. L18:791 excites
  5. L16:527 excites
  6. L17:642 excites
  7. L17:1218 excites
  8. L16:432 excites period after month or initial
  9. L11:1047 weakly excites pieces of software and library names
  10. L16:826 weakly excites
  11. L18:113 weakly suppresses
  12. L15:2237 weakly excites
  13. L17:347 weakly suppresses full stops ending informative sentences
  14. L17:1772 weakly excites
  15. L17:11 weakly suppresses
  16. L15:2561 weakly suppresses
  17. L13:961 weakly excites
  18. L18:48 weakly excites
  19. L17:2932 weakly excites
  20. L9:1164 weakly excites
  21. L8:539 weakly suppresses
  22. L14:422 weakly suppresses periods after initials and abbreviations
  23. L10:2963 weakly excites
  24. L15:2226 weakly suppresses

Feeds later layers

  1. L24:228 strongly suppresses
  2. L25:294 strongly suppresses
  3. L20:536 strongly suppresses
  4. L26:11 strongly excites
  5. L27:319 suppresses
  6. L26:255 suppresses
  7. L25:656 suppresses
  8. L26:593 suppresses
  9. L26:1169 suppresses
  10. L25:387 suppresses
  11. L21:148 suppresses
  12. L26:174 suppresses
  13. L27:1418 suppresses
  14. L26:943 suppresses
  15. L27:25 excites
  16. L27:1328 suppresses
  17. L20:622 excites
  18. L26:62 excites
  19. L27:580 suppresses
  20. L27:385 suppresses
  21. L27:362 suppresses
  22. L20:1806 excites slash inside web addresses
  23. L22:1058 suppresses
  24. L26:1391 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.

1 values between -18.06 and -17.511 values between -9.78 and -9.221 values between -7.01 and -6.461 values between -5.91 and -5.361 values between -5.36 and -4.802 values between -4.25 and -3.705 values between -3.15 and -2.595 values between -2.59 and -2.046 values between -2.04 and -1.4913 values between -1.49 and -0.9426 values between -0.94 and -0.38906 values between -0.38 and 0.172234 values between 0.17 and 0.72643 values between 0.72 and 1.2761 values between 1.27 and 1.831 values between 1.83 and 2.381 values between 3.48 and 4.04offnegativepositiveoften

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. 亞
  2. いたら
  3. ⏎
  4. %m
  5. HasForeignKey
  6. 是为了
  7. %
  8. 第二
  9. 同一
  10. 虽然

Suppresses

  1. .\
  2. .`
  3. .]
  4. .)
  5. .;
  6. .�
  7. .:
  8. .'
  9. .”
  10. .,