Neuron Explorer

Qwen3-0.6B

indefinite article before a noun

A neuron in layer 10 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 fires on the words 'a' or 'an' that come right before a noun phrase, such as 'from a common ancestor' or 'on a small mountain'. It seems to be getting ready for the noun that follows. Turning it up did not produce a clear theme in the written output.

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

    of those things if evolution were true."⏎Austin wondered about the evolutionists' claim that human and ape DNA are so alike, it proves man and ape evolved from a common ancestor.and thus proves evolution.⏎Lisle pointed out their DNA does have many

  2. #2 peak

    URE as we should, we need to understand first of all that culture is a superstructure⏎thatrests upon a material basis.⏎The ideas, institutions and all cultural patterns are dependent on the material

  3. #3 peak

    Supreme Court’s decision inBrown v. Board of Educationis widely considered a seminal point in the battle to end segregation, but it was in fact the culmination of a decades-long legal campaign.Root and Branchis the epic story of the two fiercely dedicated

  4. #4 peak

    a default in lieu.⏎When the 406 Not Acceptable error message is received, it is in response to an HTTP request that includes a negation-related header such as Accept or Accept-Language.

  5. #5 peak

    o. Phnom Da in Takeo is one of the popular tourist attractions in Takeo.⏎Phnom Da, Takeo is a temple which was constructed on a small mountain. It was built in the 6th century by the King Rut

  6. #6 peak

    .⏎© Science Museum / Science & Society Picture Library<|endoftext|>Note: This lesson was originally published on an older version of The Learning Network; the link to the related Times article will take

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 will be in the country" in the park, and I will be there. And I will be there. And I will be there. And I will be there. And I will be there. And I will be there.

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 learning is your purpose, you might have to invest a little to get valuable, extensive worksheets that actually assist your child to learn.⏎Worksheets that have been developed by a preschool instructor that knows what the school demands are and also what your youngster

  2. #2 peak

    fully accepted the highly abstract nature of Heisenberg's quantum mechanics, says Miller. They agreed with Galileo's assertion that "the book of nature is written in mathematics", but they also realized the power of using visual imagery to represent mathematical symbols

  3. #3 peak

    volcanoes, tsunamis, global climate, and weather.⏎Based on your research, do the following:⏎Support your statements with examples. Use a minimum of six reliable references, two of which should be peer-reviewed articles.⏎Write a

  4. #4 peak

    Christo Luksatrio, to encourage his program to educate students on 360 technology.⏎Luksatrio, who works as a technology development assistant for the School of Professional Communication, said he wanted to experiment with this type of

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. L5:225 suppresses
  2. L9:656 excites
  3. L6:426 excites
  4. L8:191 suppresses
  5. L9:1081 excites
  6. L4:49 excites
  7. L7:298 suppresses
  8. L8:619 suppresses
  9. L9:457 excites
  10. L7:1880 suppresses
  11. L7:155 weakly suppresses
  12. L8:1997 weakly excites
  13. L8:193 weakly suppresses
  14. L8:294 weakly suppresses
  15. L9:942 weakly excites
  16. L2:1062 weakly excites
  17. L7:959 weakly excites
  18. L9:1724 weakly suppresses
  19. L9:1084 weakly suppresses
  20. L9:1811 weakly suppresses
  21. L8:1172 weakly excites
  22. L9:1228 weakly suppresses
  23. L7:1326 weakly suppresses
  24. L8:1000 weakly excites names of agencies and institutions

Feeds later layers

  1. L15:2513 excites
  2. L14:359 suppresses
  3. L12:966 excites
  4. L11:1257 suppresses
  5. L11:1960 excites
  6. L11:679 excites
  7. L18:717 suppresses
  8. L15:834 excites
  9. L11:1367 excites
  10. L12:1255 excites
  11. L14:1168 weakly excites
  12. L11:2336 weakly excites
  13. L18:1740 weakly suppresses
  14. L11:2087 weakly excites
  15. L13:2074 weakly excites
  16. L12:442 weakly suppresses
  17. L15:826 weakly suppresses
  18. L16:1178 weakly excites
  19. L13:1949 weakly excites
  20. L12:2041 weakly excites
  21. L16:2340 weakly excites
  22. L16:2643 weakly excites
  23. L19:1022 weakly suppresses
  24. L17:1542 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 -2.19 and -2.001 values between -1.42 and -1.231 values between -1.23 and -1.048 values between -1.04 and -0.8511 values between -0.85 and -0.6643 values between -0.66 and -0.47200 values between -0.47 and -0.28750 values between -0.28 and -0.092344 values between -0.09 and 0.11374 values between 0.11 and 0.3089 values between 0.30 and 0.4931 values between 0.49 and 0.6818 values between 0.68 and 0.8713 values between 0.87 and 1.068 values between 1.06 and 1.254 values between 1.25 and 1.444 values between 1.44 and 1.632 values between 1.63 and 1.821 values between 1.82 and 2.013 values between 2.40 and 2.592 values between 5.26 and 5.45offnegativepositiveoften

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. 又要
  2. setContent
  3. addCriterion
  4. oire
  5. 另一方面
  6. .setCursor
  7. 又是
  8. (PyObject
  9. ubishi
  10. 的对象

Suppresses

  1. 当
  2. bid
  3. lyph
  4. 当他
  5. thic
  6. rown
  7. even
  8. Atom
  9. Im
  10. bart