Neuron Explorer

Qwen3-0.6B

unclear: mid-sentence function words

A neuron in layer 15 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

It fires on small connecting words in the middle of a sentence, like 'a', 'of', 'in' or 'up', where the phrase is clearly about to continue. It is hard to name one clear topic. When it was turned up, the model's writing became repetitive and wandered off, with no clear theme.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

    (IORefs/STRefs for example).⏎> One way to avoid that is for the leaves to refer to their objects⏎> through a Map. Then changing a leaf object requires only that the value⏎> associated with key represented by the leaf

  2. #2 peak

    en.]⏎Orthography: The Cleasby & Vigfusson book used letter ö to represent the original Old Norse vowel ǫ. Therefore, bröstuliga may be more accurately written as brǫstuliga.⏎Possible run

  3. #3 peak

    life on Mars, and before tech billionaires started threatening to send people to space.⏎So if NASA’s Planetary Protection Officer—there is one—is going to live up to the coolest job title in the solar system, the space agency is going to

  4. #4 peak

    , from generation to generation. - (C.7323)<|endoftext|>EffectivenessA blood pressure reading consists of two numbers -- for example: 120/80. The top number is known as the systolic blood pressure

  5. #5 peak

    think about the matter of teen sex. What, she asked, are the real consequences of sexual precocity?⏎To fully understand Meier’s motivation, we must rewind to 1996, when

  6. #6 peak

    around which the entire northern sky appears to turn. That is because Polaris is located more or less above the northern axis of the Earth, and the wheeling of the stars across the dome of night is really due to Earth’s turning, after

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: and I want to share my thoughts in the case of the most powerful effort of my greatest efforts and the most powerful effort of my most powerful effort of my and of the most powerful effort of my most powerful effort of my and of of my

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

    outcomes between regular and advanced economics classes. Finally, the authors find that students in advanced economics classes significantly outperform students in regular classes.⏎If you experience problems downloading a file, check if you have the proper application to view it first. In case

  2. #2 peak

    |⏎|Estimated Time||50 minutes (or a series of minilessons)|⏎When teaching a lesson on descriptive writing, students may write descriptively in the moment,

  3. #3 peak

    a historic event of such significance. Here, you will find useful tips, guidelines and possible topics that might be interesting to write in your paper on history.⏎Writing a paper on history requires you providing lots of information and historical details within the given amount

  4. #4 peak

    Specific, Measurable, Attainable, Relevant, and Time Bound. Setting a goal and seeing it through to completion requires careful planning and consideration.⏎When setting a S.M.A.R.T goal, it is important to be specific about what you

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. L14:1288 strongly suppresses
  2. L14:2194 suppresses
  3. L13:943 excites
  4. L14:1608 suppresses
  5. L14:1463 suppresses
  6. L13:1071 excites
  7. L13:958 excites
  8. L13:1711 excites
  9. L13:1434 suppresses
  10. L13:359 suppresses
  11. L12:1660 suppresses
  12. L13:401 excites
  13. L13:487 excites
  14. L13:1343 suppresses
  15. L14:2325 suppresses
  16. L14:2999 suppresses
  17. L13:891 suppresses
  18. L13:516 suppresses
  19. L14:1526 excites
  20. L14:1193 suppresses
  21. L12:210 suppresses
  22. L14:2118 suppresses
  23. L14:924 suppresses
  24. L14:186 suppresses

Feeds later layers

  1. L16:1265 suppresses
  2. L17:1502 excites
  3. L18:1187 excites
  4. L17:1640 excites
  5. L16:1342 excites
  6. L17:2496 suppresses
  7. L16:2869 excites
  8. L16:1802 excites
  9. L18:658 excites
  10. L18:1414 excites
  11. L16:411 excites
  12. L20:210 excites
  13. L16:1587 suppresses
  14. L16:397 excites
  15. L18:1003 excites
  16. L16:320 excites
  17. L16:1719 suppresses
  18. L16:1646 excites
  19. L17:1746 excites
  20. L21:881 excites comma after 'if' clause in prose, braces in code
  21. L19:1475 weakly suppresses
  22. L16:669 weakly suppresses
  23. L16:931 weakly suppresses
  24. L17:200 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 -1.64 and -1.542 values between -1.16 and -1.071 values between -0.97 and -0.881 values between -0.88 and -0.783 values between -0.78 and -0.698 values between -0.69 and -0.5912 values between -0.59 and -0.4947 values between -0.49 and -0.40166 values between -0.40 and -0.30346 values between -0.30 and -0.21721 values between -0.21 and -0.111064 values between -0.11 and -0.021107 values between -0.02 and 0.08281 values between 0.08 and 0.1778 values between 0.17 and 0.2737 values between 0.27 and 0.366 values between 0.36 and 0.464 values between 0.46 and 0.555 values between 0.55 and 0.654 values between 0.65 and 0.741 values between 0.74 and 0.845 values between 0.84 and 0.931 values between 0.93 and 1.033 values between 1.13 and 1.222 values between 1.22 and 1.321 values between 1.32 and 1.411 values between 2.08 and 2.17offnegativepositiveoften

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. uling
  2. dạ
  3. olars
  4. usher
  5. athing
  6. '<%=
  7. 系统的
  8. ◢
  9. 天涯
  10. putc

Suppresses

  1. omon
  2. sav
  3. sez
  4. 麦克
  5. subclass
  6. regor
  7. pecially
  8. �
  9. logue
  10. 小康