Neuron Explorer

Qwen3-0.6B

comma closing a main clause

A neuron in layer 1 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 commas that come right after a complete statement, where the sentence is about to add an extra detail. It is a weak signal. When turned up, the model's replies wandered into unrelated topics, so the steering result does not confirm the pattern.

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

    precarious world. During attacks, the rural populace could flee behind city walls, where defence forces assembled to repel the enemy. The wall served this purpose for millennia, until the invention of heavy artillery rendered walls useless in warfare. With the advent of

  2. #2 peak

    Berkeley. It’s a comprehensive resource for learning more about the processes of science as used in the real world. The processes of science are represented as fluid and iterative, showing that science does not follow a structured recipe. The three

  3. #3 peak

    istic period. Known for their strongly realistic portraits, this tetradrachm of Eukratides is no exception. He is depicted as a formidable warrior, wearing a cuirass and a bronze helmet over his diadem. His features

  4. #4 peak

    how hard the local population work, they remain the poorest of the poor.⏎The Tam Nông Hospital is an old hospital built in the early 80s, originally intended for 20 beds.⏎Tam Nông Hospital⏎Due to the

  5. #5 peak

    multi-core paradigm. The microprocessor has proven to be a versatile invention, branching out into numerous fields outside the personal computer.⏎Microprocessors have revolutionized the world, especially in the area of electronics. A myriad of modern items ranging from cell phones

  6. #6 peak

    and Lorraine families. The Medici collection began in the 16th century, first in Palazzo Vecchio, then at the Uffizi and finally 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: I have a 4-digit number, the number of 3-digit numbers, and the number of 2-digit numbers. Maybe, I have a 1-digit number. Perhaps, I have a 0-digit number. So, I

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

    implemented, for example, by the laws of King Benjamin and Mosiah. Yet they were constantly reminded that salvation does not come by the law of Moses:⏎“And, notwithstanding we believe in Christ, we keep the law of Moses, and look forward

  2. #2 peak

    roads are not necessarily the best solution.The statistics on car ownership and per capita income suggest that planners should start to think in a different way about road transport – and, indeed, about air transport – in Papua New Guinea. For the foreseeable future,

  3. #3 peak

    called impersonal verbs.⏎An impersonal verb is one that has no determinate subject.⏎Sometimes the subject is not represented at all; as, Methinks, meaning, it seems to me; lists, meaning, it ple

  4. #4 peak

    the class and helping the class become a successful place of learning.⏎The instructor presented a survey to the students on the first day about the merit of participation; and, how participation can affect the class.⏎The first function of the research plan focuses on

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. L0:1301 weakly suppresses
  2. L0:1224 weakly suppresses
  3. L0:178 weakly suppresses
  4. L0:1596 weakly excites
  5. L0:313 weakly suppresses "and" joining paired nouns
  6. L0:68 weakly suppresses
  7. L0:925 weakly excites
  8. L0:1961 weakly suppresses
  9. L0:80 weakly excites
  10. L0:2195 weakly excites
  11. L0:1595 weakly excites
  12. L0:1001 weakly suppresses
  13. L0:2479 weakly suppresses
  14. L0:573 weakly suppresses
  15. L0:2296 weakly excites
  16. L0:2573 weakly excites
  17. L0:1260 weakly excites
  18. L0:148 weakly suppresses
  19. L0:98 weakly suppresses
  20. L0:1753 weakly excites
  21. L0:1497 weakly suppresses
  22. L0:1000 weakly excites
  23. L0:2475 weakly suppresses
  24. L0:2005 weakly excites

Feeds later layers

  1. L16:695 weakly excites
  2. L14:1639 weakly excites "and" joining two nouns
  3. L11:2039 weakly excites
  4. L13:0 weakly excites
  5. L16:450 weakly excites
  6. L16:1489 weakly excites
  7. L6:1937 weakly suppresses
  8. L16:42 weakly excites
  9. L18:2956 weakly suppresses
  10. L2:12 weakly suppresses
  11. L13:491 weakly excites
  12. L16:319 weakly excites
  13. L6:2410 weakly suppresses
  14. L10:2268 weakly suppresses
  15. L20:2731 weakly suppresses
  16. L18:12 weakly excites
  17. L18:54 weakly excites
  18. L10:95 weakly excites
  19. L16:480 weakly excites
  20. L13:518 weakly suppresses
  21. L9:661 weakly excites
  22. L19:1541 weakly excites
  23. L4:2903 weakly excites
  24. L2:2367 weakly 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 -2.14 and -2.021 values between -1.19 and -1.071 values between -0.95 and -0.831 values between -0.71 and -0.592 values between -0.59 and -0.478 values between -0.47 and -0.35109 values between -0.35 and -0.23467 values between -0.23 and -0.111488 values between -0.11 and 0.011257 values between 0.01 and 0.13386 values between 0.13 and 0.2566 values between 0.25 and 0.3711 values between 0.37 and 0.4912 values between 0.49 and 0.6114 values between 0.61 and 0.7311 values between 0.73 and 0.858 values between 0.85 and 0.979 values between 0.97 and 1.099 values between 1.09 and 1.2110 values between 1.21 and 1.334 values between 1.33 and 1.455 values between 1.45 and 1.568 values between 1.56 and 1.688 values between 1.68 and 1.804 values between 1.80 and 1.924 values between 1.92 and 2.041 values between 2.16 and 2.281 values between 2.40 and 2.522 values between 2.52 and 2.64offnegativepositiveoften

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. dere
  2. others
  3. jq
  4. kür
  5. rés
  6. _PHP
  7. izable
  8. 大国
  9. doubleValue
  10. .TextAlign

Suppresses

  1. emos
  2. elines
  3. ��
  4. `,
  5. },{
  6. ination
  7. abol
  8. nữa
  9. 께
  10. .),