Neuron Explorer

Qwen3-0.6B

'the' after 'indicate' or 'is'

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 word 'the' when it comes right after verbs like 'indicate' or 'is', as in 'indicating the most job losses'. Its negative side is weaker and points at words in lists of punctuation or markup. Turning it up did not give a clear, consistent 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

    011 to 2020. Each district within a state is given one of four distinct shades of reddish brown, with the darkest color indicating the most job losses and the lightest color showing the least. The range of job

  2. #2 peak

    called "Session Laws" or "Statutes at Large."⏎Bill Number: Bills are referred to by number. The number really has two parts: the abbreviation for the specific wing of the legislature in which the bill is introduced, as in HB (

  3. #3 peak

    escape sequences to print special characters, tabs, or line breaks Escape sequences start with a backslash ( `` ). Some common escape sequences are: - `n` Newline - Prints a newline character - `t ` Tab - Prints a tab character

  4. #4 peak

    biking to school and slow down, especially in residential areas and school zones. Motorists should know what the yellow and red bus signals mean. Yellow flashing lights indicate the bus is getting ready to stop and motorists should slow down and be prepared to stop

  5. #5 peak

    noise levels, acoustical ceiling panels should have a noise reduction coefficient (NRC) of 0.70 or greater. (The NRC indicates the average percentage of sound a material absorbs; an NRC of 0.7

  6. #6 peak

    coiled, linear and open form of DNA?⏎The equation for calculating extinction coefficients is stated by Beer's Law:⏎A = epsilon.c.l⏎Where A is the absorbance measurement at a given wavelength⏎epsilon is the extinction coefficient in M^-

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 know that, as a human, I have always been in the position of a student who has a deep appreciation for the arts, and I have always been in a position of access, and I have always been part of a community of

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

    in HTML. </BODY> </HTML>When this is displayed by Mosaic, it will look like:⏎As you can probably guess, commands are enclosed in angle-brackets <>, so that the HTML command <TITLE> means that the following

  2. #2 peak

    time: Servitude today?⏎(To receive these entries when they are posted, go to the upper right hand corner of the top banner and click on the three dots or parallel lines. Scroll down to the subscription form and enter your information.)<|endoftext|>

  3. #3 peak

    0 words not including the questions. Questions in bold then answers.APA 7th addition format⏎Post an explanation of the effects

  4. #4 peak

    when you have single quotation marks inside a string to avoid quote exceptions. Similarly, wrap the string in single

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. L9:11 excites
  2. L7:949 weakly suppresses
  3. L9:900 weakly excites
  4. L9:3044 weakly suppresses
  5. L8:1007 weakly suppresses
  6. L8:288 weakly excites
  7. L2:2124 weakly excites
  8. L7:211 weakly excites
  9. L6:82 weakly suppresses
  10. L0:2081 weakly suppresses
  11. L4:2463 weakly suppresses
  12. L3:2179 weakly excites
  13. L0:2520 weakly suppresses
  14. L5:569 weakly excites
  15. L1:1827 weakly excites
  16. L5:2208 weakly suppresses
  17. L7:271 weakly excites
  18. L4:2116 weakly excites
  19. L2:867 weakly suppresses
  20. L8:1512 weakly excites
  21. L2:2232 weakly excites
  22. L4:735 weakly excites
  23. L2:759 weakly excites
  24. L7:1082 weakly suppresses

Feeds later layers

  1. L12:363 excites
  2. L13:2686 excites
  3. L13:1363 excites
  4. L13:2607 excites
  5. L11:575 excites
  6. L13:1420 excites
  7. L13:116 suppresses
  8. L13:2370 suppresses
  9. L14:1439 excites
  10. L12:3064 excites
  11. L14:1720 excites
  12. L15:1397 suppresses
  13. L13:1570 weakly suppresses
  14. L11:572 weakly suppresses
  15. L13:1191 weakly excites
  16. L15:2053 weakly excites
  17. L11:948 weakly suppresses
  18. L14:770 weakly excites
  19. L14:236 weakly suppresses 'and' joining two parallel subjects
  20. L14:503 weakly suppresses
  21. L15:1576 weakly excites
  22. L12:1223 weakly excites
  23. L11:255 weakly suppresses
  24. L12:460 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 -1.19 and -1.101 values between -1.10 and -1.011 values between -0.72 and -0.633 values between -0.63 and -0.5412 values between -0.54 and -0.4434 values between -0.44 and -0.35124 values between -0.35 and -0.25292 values between -0.25 and -0.16652 values between -0.16 and -0.071334 values between -0.07 and 0.03799 values between 0.03 and 0.12413 values between 0.12 and 0.22156 values between 0.22 and 0.3148 values between 0.31 and 0.4119 values between 0.41 and 0.505 values between 0.50 and 0.593 values between 0.69 and 0.783 values between 0.78 and 0.882 values between 0.88 and 0.971 values between 0.97 and 1.061 values between 1.06 and 1.161 values between 1.35 and 1.441 values between 1.54 and 1.631 values between 1.63 and 1.721 values between 2.48 and 2.57offnegativepositiveoften

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. ственный
  2. /orders
  3. annon
  4. aste
  5. ;%
  6. unte
  7. instant
  8. instant
  9. ASTE
  10. quests

Suppresses

  1. ModelError
  2. ***!⏎
  3. ombine
  4. PropertyDescriptor
  5. ệt
  6. AndView
  7. 的人来说
  8. なりません
  9. tdown
  10. asticsearch