Neuron Explorer

Qwen3-0.6B

naming words for terms and labels

A neuron in layer 6 of Qwen3-0.6B. Its strongest snippets are fairly consistent: several of them peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron responds to words that name or label something, such as name, keywords, identifiers, and symbol, usually where the text is about what a thing is called. Its strongest negative cases are grammar terms like conditional and superlative, and turning it up gave no clear theme.

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

    ” or “https://”) is highly recommended. This allows to trace the information online, even if it becomes outdated.⏎The citing of DOIs (digital object identifiers) is encouraged.⏎Citing the date when an online work was consulted is now

  2. #2 peak

    this asteroid for more than a decade,” said Dante Lauretta, principal investigator for the mission at the University of Arizona. “We look forward to having a name that is easier to say than (101955) 1

  3. #3 peak

    remedied. Sign up now while there is still space in this special course!⏎Lessons cover issues such as the acknowledgment of God, Marriage, Life, Obscenity, Immigration, Parents’ Rights, Elections, Criminal Law, and the citing

  4. #4 peak

    .⏎Both episodes were probably taken into account when the monks of St Basil originally selected a name for their leper hospital. The name eventually gave rise to the terms "lazar", meaning a leper, and

  5. #5 peak

    process of improving the visibility of a website or webpage in search engine results.SEO considers how search engines work, what people search for, the actual search terms or keywords typed into search engines, and which search engines are preferred by their targeted

  6. #6 peak

    for so many errors have been introduced and ingrafted into their religion, by their ignorance, their separation from the Catholic Church, and their intercourse with Jews, Pagans, and Mohammedans, that their present religion is nothing but a kind of confused

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 first" is not a place, and the second is not a place. What is the function of the verb in this case? The sentence is: "The first is not a place, and the second is not a place.

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

    students are confused about verbs, nouns and adjectives. Imagine what happens once they begin to stumble across the imperfect subjunctive, the pluperfect and the conditional! ¡Flipan en colores!⏎The

  2. #2 peak

    ," he is expressing a comparison price.⏎The effect that produces the adjective superlative communication consists of raising the quality of a noun. However, although the adverb very and the suffix isimo are very

  3. #3 peak

    (8) Had his father not died? (9) They had returned the home? (10)You had finished this book?⏎Past Perfect Tense Negative⏎Subject + had not + verb 3rd from + object.⏎Past Perfect

  4. #4 peak

    . The adverb "yesterday" makes it clear that the action was in the past. The

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. L4:2995 suppresses
  2. L4:1040 suppresses
  3. L3:698 excites
  4. L4:2119 weakly excites
  5. L5:2177 weakly suppresses
  6. L3:694 weakly suppresses
  7. L5:1764 weakly excites
  8. L4:1874 weakly excites
  9. L5:1981 weakly excites
  10. L2:296 weakly suppresses
  11. L4:785 weakly suppresses
  12. L2:606 weakly suppresses
  13. L5:2145 weakly suppresses
  14. L4:2253 weakly suppresses
  15. L5:1163 weakly suppresses
  16. L5:341 weakly suppresses
  17. L4:906 weakly suppresses
  18. L3:1896 weakly excites
  19. L4:2894 weakly suppresses
  20. L5:1720 weakly suppresses
  21. L2:2404 weakly excites
  22. L0:926 weakly excites
  23. L2:1573 weakly excites
  24. L1:2478 weakly suppresses

Feeds later layers

  1. L8:2527 suppresses
  2. L11:1687 suppresses
  3. L10:1051 suppresses
  4. L8:2271 suppresses
  5. L9:1913 suppresses
  6. L8:1497 suppresses
  7. L7:2813 suppresses
  8. L11:1544 suppresses
  9. L7:983 suppresses
  10. L8:1085 suppresses
  11. L19:2158 suppresses
  12. L8:1007 suppresses
  13. L10:653 excites
  14. L7:2809 weakly suppresses
  15. L7:1150 weakly suppresses
  16. L10:592 weakly suppresses
  17. L8:2148 weakly suppresses
  18. L19:1913 weakly suppresses
  19. L7:2033 weakly suppresses
  20. L12:2197 weakly suppresses
  21. L18:1257 weakly suppresses
  22. L10:542 weakly suppresses word completing a technical term
  23. L18:1777 weakly suppresses
  24. L26:2770 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 -3.09 and -2.981 values between -2.55 and -2.441 values between -1.89 and -1.781 values between -1.46 and -1.351 values between -1.24 and -1.132 values between -1.13 and -1.022 values between -1.02 and -0.916 values between -0.91 and -0.805 values between -0.80 and -0.695 values between -0.69 and -0.5911 values between -0.59 and -0.4832 values between -0.48 and -0.3790 values between -0.37 and -0.26295 values between -0.26 and -0.15915 values between -0.15 and -0.041729 values between -0.04 and 0.07565 values between 0.07 and 0.18176 values between 0.18 and 0.2939 values between 0.29 and 0.4016 values between 0.40 and 0.515 values between 0.51 and 0.625 values between 0.62 and 0.722 values between 0.72 and 0.832 values between 0.83 and 0.941 values between 1.16 and 1.27offnegativepositiveoften

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. anning
  2. 服务能力
  3. 录制
  4. ATURE
  5. inaire
  6. vida
  7. ARING
  8. .ASCII
  9. 乾坤
  10. 神州

Suppresses

  1. sub
  2. いません
  3. implies
  4. (crate
  5. not
  6. 论
  7. 三是
  8. odem
  9. ��
  10. Authors