Neuron Explorer

Qwen3-0.6B

'other' in 'and other ...' lists

A neuron in layer 12 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 reacts to the word 'other' when it follows 'and' in a list, as in 'roads, buildings, and other infrastructure'. It is steadily strong on that word. Turning it up did not make the writing obviously about lists, though.

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

    silver plate, including crosses, chalices, and other spoils of the Church might be as much more. These movables were before

  2. #2 peak

    .⏎(ii) Similarly, the boycott of British institutions posed a problem. No alternative institutions were set-up in their . place. So, the students, teachers and other professionals finally had to resume their studies and jobs in government institutions like schools, colleges

  3. #3 peak

    ulates that rice husk ash could replace up to 20% of the cement typically mixed into concrete for the construction of skyscrapers, bridges, and other structures, dramatically reducing carbon dioxide. Every ton of cement manufactured for use in concrete

  4. #4 peak

    /French (N.Y. &N.F.) is the third supporting idea. * Amerindians forced to do unpaid labor to build roads, buildings, and other infrastructure in towns through the Encomienda System (S.W.) * The N

  5. #5 peak

    lowercase," they told us. There would be dire consequences, such as bad handwriting, nervousness, stuttering, and, in general, the self-defeating attitudes that often accompany the too-early introduction of formal

  6. #6 peak

    to schedule any kind of task you can imagine. It's useful for sending emails about system or program statistics, performing regular system maintenance, running backups, or doing any other task you can think of. There are similar programs on other operating

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 time of the hour (or the hour) and the time of the hour (or the hour) and the time of the hour (or the hour) and the time of the hour (or the hour) and the time of the

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

    Writing⏎- HR Interview Questions⏎- Computer Glossary⏎- Who is Who⏎Demand & Elasticities⏎The 'Law Of Demand' states that, all other factors being equal, as the price of a good or service increases, consumer demand

  2. #2 peak

    of more/less entrants into the market, and the changing of consumer preferences. The shift can either be parallel or nonparallel.⏎Extension of Demand⏎Other things remaining constant, when more quantity is demanded at a lower price, it is called

  3. #3 peak

    vessel, although Inmarsat does provide broadband service for maritime communications using all 14 satellites. Regular terminals also cannot be used on aircraft.⏎Join thousands of others with our weekly newsletter⏎The 4th Era of IT Infrastructure: Supercon

  4. #4 peak

    could possibly test the hypothesis; and must document in the hypothesis just HOW the hypothesis will be tested. The tests or experiments must be rigorous enough, that there is a big chance that his or her

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. L10:1219 suppresses
  2. L6:2654 suppresses
  3. L3:2029 weakly excites
  4. L10:2724 weakly excites
  5. L7:1714 weakly excites
  6. L11:706 weakly suppresses
  7. L6:1376 weakly excites
  8. L7:2691 weakly excites
  9. L3:2209 weakly excites
  10. L6:1977 weakly suppresses
  11. L3:1147 weakly suppresses
  12. L8:641 weakly excites
  13. L5:2356 weakly excites
  14. L9:557 weakly excites
  15. L5:2560 weakly excites
  16. L9:285 weakly suppresses
  17. L10:985 weakly suppresses
  18. L6:527 weakly suppresses
  19. L2:2088 weakly excites
  20. L8:1137 weakly suppresses
  21. L7:601 weakly excites
  22. L1:1302 weakly suppresses
  23. L5:1327 weakly excites
  24. L8:838 weakly excites

Feeds later layers

  1. L14:980 excites
  2. L14:1485 excites
  3. L18:1850 excites
  4. L19:1754 weakly excites
  5. L13:2409 weakly excites
  6. L15:2824 weakly excites
  7. L15:2393 weakly excites
  8. L27:922 weakly excites
  9. L13:2234 weakly excites
  10. L20:1708 weakly suppresses
  11. L13:1546 weakly excites
  12. L19:2121 weakly excites
  13. L13:2808 weakly excites
  14. L16:1212 weakly excites
  15. L15:2137 weakly excites
  16. L15:1372 weakly excites 'other' after 'any', 'all' or 'or'
  17. L17:2187 weakly excites 'etc' ending a list
  18. L15:609 weakly suppresses
  19. L14:2521 weakly suppresses
  20. L15:126 weakly excites
  21. L14:1821 weakly excites
  22. L20:2104 weakly suppresses
  23. L15:3069 weakly excites
  24. L15:2322 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 -1.86 and -1.734 values between -1.11 and -0.982 values between -0.98 and -0.858 values between -0.85 and -0.7313 values between -0.73 and -0.6035 values between -0.60 and -0.4890 values between -0.48 and -0.35234 values between -0.35 and -0.23541 values between -0.23 and -0.101458 values between -0.10 and 0.02972 values between 0.02 and 0.15372 values between 0.15 and 0.27105 values between 0.27 and 0.4034 values between 0.40 and 0.5213 values between 0.52 and 0.653 values between 0.65 and 0.775 values between 0.77 and 0.901 values between 0.90 and 1.022 values between 1.02 and 1.153 values between 1.15 and 1.274 values between 1.27 and 1.401 values between 1.40 and 1.523 values between 1.52 and 1.651 values between 1.65 and 1.771 values between 1.77 and 1.901 values between 2.27 and 2.401 values between 3.03 and 3.15offnegativepositiveoften

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. other
  2. Other
  3. Other
  4. other
  5. 其他
  6. aside
  7. yên
  8. 诸
  9. 其它
  10. blend

Suppresses

  1. rese
  2. #w
  3. aurant
  4. isu
  5. wers
  6. ikt
  7. printed
  8. tere
  9. cus
  10. atis