Neuron Explorer

Qwen3-0.6B

time of day before a clock time

A neuron in layer 23 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 empty spot right after words like "at", "to", or "from" where a clock time is about to come, such as "open until 4:30 p.m.". Turning it up gave text that repeated words, so the steering results are not a clear match.

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

    .⏎Visit our Ed Clark Museum of Missouri Geology on Geologic Map Day to learn more about geologic maps. Open weekdays from 8 a.m. to 4:30 p.m., we are located at 111 Fair

  2. #2 peak

    coding is waiting for you, and it fits in the palm of your hand.⏎Have an amazing project to share? The Electronics Show and Tell is every Wednesday at 7pm ET! To join, head over to YouTube<|endoftext|>Definition of Parab

  3. #3 peak

    to allow its black patrons to eat at its lunch counter. Though they received no service, the four men sat quietly and without incident. When the store closed at 5:30, they left.⏎The next morning, the four young men

  4. #4 peak

    theoretical possibility of space flight, but built and flew the world’s first liquid propellant rockets.”⏎The event will take place from 10 a.m. to 3 p.m. on Saturday, June 11, on the Mall in

  5. #5 peak

    for each session. The camp will meet daily Monday – Friday from 9am – 4pm.<|endoftext|>People with diabetes are at increased risk of

  6. #6 peak

    am sure you are all raring to go!!⏎I am going to set up a 'Zoom' meeting on Thursday 14th May at 12pm as I have had lots of emails from you and your parents saying

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: what if we have a random family of random variables that are all independently and independently randomly randomly randomly random. I need to solve this for a random family of random variables. I think I have a correct family of random variables that satisfies this,

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 I wrote this document.⏎QRcode is developed by DENSO Corporation. It is standardized by JIS and ISO.⏎This document is based on JIS X 0510(1999).⏎If you want to know more

  2. #2 peak

    only mathematicians - like to consider more specific questions in order to get some feeling for what is happening. In this article we will reflect about a special class of Lunda-designs.⏎On the day before my daughter Likilisa's fourth birthday

  3. #3 peak

    engagements. During World War II, four battles took place for control of the city: The city was captured and recaptured by Nazi Germany on 24 October 1941; there was a disastrous Red Army offensive that failed to capture

  4. #4 peak

    provider:|| Postal: Katajanokanlaituri 6B, 00160 Helsinki|⏎Web page: http://www.wider.un

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. L21:128 excites
  2. L3:461 excites
  3. L20:293 suppresses
  4. L21:1328 weakly suppresses
  5. L21:2349 weakly excites
  6. L16:566 weakly suppresses unclear: mid-sentence word choices, mixed
  7. L9:693 weakly suppresses
  8. L16:2997 weakly excites
  9. L4:739 weakly suppresses
  10. L0:1277 weakly excites
  11. L10:276 weakly excites
  12. L10:2435 weakly excites
  13. L4:1681 weakly excites
  14. L22:1048 weakly suppresses
  15. L13:1479 weakly suppresses
  16. L10:2217 weakly suppresses
  17. L10:455 weakly excites
  18. L9:65 weakly suppresses
  19. L3:531 weakly excites
  20. L4:1542 weakly suppresses
  21. L10:1458 weakly excites
  22. L15:1616 weakly suppresses word fragments mid-word
  23. L19:1103 weakly suppresses
  24. L18:408 weakly excites

Feeds later layers

  1. L27:2522 weakly excites
  2. L24:2837 weakly excites
  3. L24:1562 weakly suppresses
  4. L25:324 weakly excites
  5. L26:1234 weakly suppresses
  6. L25:1709 weakly excites
  7. L27:1320 weakly excites
  8. L25:2735 weakly excites
  9. L26:2522 weakly suppresses
  10. L24:1066 weakly excites
  11. L25:2792 weakly excites
  12. L24:627 weakly excites
  13. L25:2444 weakly excites
  14. L25:1346 weakly excites
  15. L25:124 weakly excites
  16. L24:2531 weakly excites
  17. L24:293 weakly excites
  18. L24:1041 weakly suppresses
  19. L24:2703 weakly suppresses
  20. L26:1263 weakly excites
  21. L24:2310 weakly suppresses
  22. L27:1311 weakly suppresses
  23. L25:1953 weakly suppresses
  24. L24:2445 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 -10.02 and -9.351 values between -8.01 and -7.343 values between -6.67 and -6.002 values between -5.33 and -4.661 values between -4.66 and -3.993 values between -3.99 and -3.322 values between -3.32 and -2.652 values between -2.65 and -1.9811 values between -1.98 and -1.3174 values between -1.31 and -0.641575 values between -0.64 and 0.032109 values between 0.03 and 0.70104 values between 0.70 and 1.379 values between 1.37 and 2.043 values between 2.04 and 2.712 values between 2.71 and 3.381 values between 3.38 and 4.052 values between 4.72 and 5.391 values between 5.39 and 6.061 values between 15.44 and 16.111 values between 16.11 and 16.78offnegativepositiveoften

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. measure
  2. جه
  3. 纥
  4. mes
  5. .Measure
  6. bek
  7. andin
  8. regulation
  9. isper
  10. inar

Suppresses

  1. 穿梭
  2. nage
  3. tastes
  4. apsed
  5. randomly
  6. herits
  7. entious
  8. [random
  9. giấc
  10. apers