Neuron Explorer

Qwen3-0.6B

'other' after 'any', 'all' or 'or'

A neuron in layer 15 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

Fires on the word 'other' when it follows 'any', 'all', 'or' or 'and', as in 'any other platform' or 'all other IBM services'. The pattern is very consistent in the examples. Turning it up made the model repeat phrases like 'a single person', which is only loosely related.

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

    Fraud⏎Mail fraud describes any action meant to defraud somebody that makes use of the United States Postal Service or any other interstate mail carrier. This would include any action in which somebody tries to cheat a

  2. #2 peak

    from a laboratory test. Our Environmental Health professionals will ensure testing of animals that could be infected with rabies. To stay safe, never handle a bat or any other wild animal” stated Erie County Health Commissioner, Dr. Gale R. Burstein

  3. #3 peak

    share the road with, motorcycle riders. A motorcyclist has the same rights, privileges, and responsibilities as any other motorist on the roadway.⏎“Motorcyclists will be out in force as

  4. #4 peak

    , and Scala so that you start creating your Spark projects and collaborating with other data scientists. When you sign up, you get free access to Watson Studio and all other IBM services for 30 days. Start now and take advantage of this offer

  5. #5 peak

    to finance its assets. The WACC is the minimum acceptable return that a company must earn on an existing asset base to satisfy its creditors, owners, and other providers of capital, or they will invest elsewhere.⏎The following is the WACC

  6. #6 peak

    to upload the pdf to Brightspace or Google Classroom (or any other platform you are using):⏎Have students record answers on top of the pdf⏎Yes

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 previous year, I was in a situation where I was in the of my previous relationship and it is what I thought of about the relationship. I was, and I have these things in my mind. I was what for the relationship.

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

    is available at http://www.usdoj.gov/crt/housing/housing_rluipa.htm. Below is a summary of the law’s key provisions, with illustrations of the types of cases that may violate the law.⏎⊕ RLUIPA

  2. #2 peak

    "focus" uses 5 letters: C F O S U.⏎No direct anagrams for focus found in this word list.⏎List shorter words within focus, sorted by length⏎All words formed from focus by changing one letter⏎Browse words starting

  3. #3 peak

    and begin to code.⏎Your program should read from the file . The file will describe a single post-cubist squarist

  4. #4 peak

    we said goodbye to four retired NASA space shuttles that found new museum-type homes.⏎Here's our list of the biggest science achievements this year, in order of significance:⏎1. Curiosity lands, performs science on Mars⏎Every time I

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. L11:1809 excites
  2. L9:792 weakly suppresses
  3. L14:2808 weakly suppresses
  4. L10:720 weakly suppresses
  5. L6:2600 weakly excites
  6. L12:1840 weakly excites
  7. L12:1853 weakly excites
  8. L6:2473 weakly suppresses
  9. L12:3027 weakly excites 'other' in 'and other ...' lists
  10. L13:1105 weakly suppresses
  11. L13:2818 weakly excites
  12. L2:730 weakly suppresses
  13. L12:942 weakly suppresses
  14. L14:383 weakly suppresses
  15. L7:1587 weakly suppresses
  16. L5:1944 weakly excites
  17. L1:1016 weakly suppresses
  18. L8:2280 weakly suppresses
  19. L10:49 weakly excites
  20. L2:1931 weakly excites
  21. L13:167 weakly excites
  22. L7:2552 weakly excites
  23. L9:2383 weakly suppresses
  24. L14:2904 weakly suppresses

Feeds later layers

  1. L16:1984 weakly suppresses
  2. L18:1738 weakly suppresses
  3. L24:236 weakly excites
  4. L17:2200 weakly suppresses
  5. L20:1156 weakly suppresses
  6. L21:676 weakly excites
  7. L16:2087 weakly suppresses
  8. L18:2426 weakly suppresses
  9. L18:679 weakly suppresses
  10. L16:327 weakly excites
  11. L20:2141 weakly excites
  12. L20:1271 weakly excites
  13. L17:2670 weakly excites
  14. L17:2331 weakly suppresses
  15. L16:2620 weakly suppresses
  16. L25:1152 weakly suppresses
  17. L24:521 weakly suppresses
  18. L16:1969 weakly suppresses
  19. L24:614 weakly suppresses
  20. L16:2818 weakly suppresses
  21. L19:2560 weakly excites
  22. L16:2040 weakly excites
  23. L20:2275 weakly excites
  24. L19:2989 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 -1.22 and -1.085 values between -1.08 and -0.943 values between -0.94 and -0.797 values between -0.79 and -0.6517 values between -0.65 and -0.5055 values between -0.50 and -0.36186 values between -0.36 and -0.21718 values between -0.21 and -0.071996 values between -0.07 and 0.08616 values between 0.08 and 0.22160 values between 0.22 and 0.3747 values between 0.37 and 0.5129 values between 0.51 and 0.6519 values between 0.65 and 0.8011 values between 0.80 and 0.9412 values between 0.94 and 1.096 values between 1.09 and 1.237 values between 1.23 and 1.383 values between 1.38 and 1.522 values between 1.67 and 1.812 values between 1.95 and 2.101 values between 2.10 and 2.241 values between 2.24 and 2.391 values between 2.39 and 2.531 values between 3.11 and 3.262 values between 4.41 and 4.56offnegativepositiveoften

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. possible
  2. asters
  3. ажд
  4. quires
  5. itest
  6. quier
  7. aches
  8. Possible
  9. _other
  10. ills

Suppresses

  1. defensively
  2. --------⏎
  3. IBC
  4. IFIER
  5. dad
  6. 态
  7. ère
  8. Lia
  9. latina
  10. .lastIndexOf