Neuron Explorer

Qwen3-0.6B

second half of multi-word proper names

A neuron in layer 6 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on the piece of a name that finishes a well-known institution or person, like the 'etter' in Sloan-Kettering or 'Had' in Large Hadron Collider. When it was turned up, the model's writing did not visibly change in a clear way.

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

    .⏎"As the field broadens, the need for more counselors and more thorough training will also increase," says Lauren Scheuer, a genetic counselor at Memorial Sloan-Kettering Cancer Center in New York and a graduate of the Sarah Lawrence Program. "

  2. #2 peak

    hallmark of cancer and has a well-established role in aggressive B cell malignancies.⏎To find out more, Hans-Guido Wendel and colleagues from Memorial Sloan-Kettering Cancer Center in New York analyzed genomic data from two large groups of slow-growing

  3. #3 peak

    31-kilometre-long collider; like the Large Hadron Collider, it promises to recreate conditions moments after the big bang in an effort

  4. #4 peak

    requires policymakers to embrace a common goal and to stay the course for many years, shielding scientific workers from the shifting whims of politicians.⏎The National Aeronautics and Space Administration (NASA) is the largest individual sponsor of astrophysics and planetary

  5. #5 peak

    Daytona Beach, the WACS, the Women’s Auxiliary Corps, developed a training base. Noted African American educator Mary McLeod Bethune had lobbied President Roosevelt to set up a WAC training base

  6. #6 peak

    “I was far from convinced,” says Incandela, a professor at the University of California, Santa Barbara and the former spokesperson of the CMS experiment at the Large Hadron Collider.⏎For decades, scientists had searched for the elusive Higgs boson

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: "if not... then..." and so on... for the life of me... not knowing... what the heck... with all there is... no... where there is no... none of the rest... and so on... So, this is

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

    , it would send a very fast message to the body to step back out of harm’s way. Similarly, if your stomach was empty and your body needed fuel,

  2. #2 peak

    the ip address. The number of port in computer networking is expressed in 16 bits, which means that there is a maximum of 65,536 ports on a computer. Assign the call coverage path for voice ports b7

  3. #3 peak

    way in which Windows configured the partition offset to attempt to achieve partition alignment.⏎Starting with these newer operating systems, the default partition offset is 1,048,576 bytes, exactly 1024 KB or 1

  4. #4 peak

    problem with hazardous smog, China seems dead serious on turning over a new leaf as we are now seeing a nation acknowledging the threat of climate change, and

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. L5:1899 strongly excites
  2. L5:2665 strongly suppresses
  3. L5:2136 strongly excites
  4. L5:2676 strongly excites
  5. L5:3063 strongly suppresses
  6. L5:2065 strongly suppresses
  7. L5:2708 strongly excites
  8. L5:2014 strongly suppresses
  9. L5:2971 strongly excites
  10. L5:3041 strongly suppresses
  11. L5:2206 strongly excites
  12. L5:2173 strongly excites "late" in dated phrases like "in the late 1980s"
  13. L5:297 strongly excites
  14. L5:2561 strongly excites
  15. L5:2452 strongly suppresses
  16. L5:2115 strongly excites
  17. L1:328 excites
  18. L3:1661 suppresses
  19. L5:2888 suppresses
  20. L0:1902 excites
  21. L2:1840 excites
  22. L2:693 suppresses
  23. L5:2618 excites
  24. L5:2295 suppresses

Feeds later layers

  1. L8:849 strongly excites
  2. L12:576 strongly suppresses 'of' in fixed phrases like table of contents
  3. L8:1017 strongly suppresses
  4. L9:716 strongly suppresses
  5. L14:1403 suppresses
  6. L10:129 excites
  7. L9:845 suppresses
  8. L15:2628 suppresses
  9. L10:678 suppresses
  10. L11:1384 suppresses
  11. L18:828 suppresses
  12. L16:882 suppresses
  13. L7:2370 suppresses
  14. L11:171 excites
  15. L15:1304 suppresses
  16. L20:452 excites
  17. L13:1513 suppresses
  18. L17:892 suppresses
  19. L10:952 excites
  20. L13:2328 excites
  21. L13:450 excites
  22. L19:2054 suppresses
  23. L19:1385 suppresses
  24. L18:819 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 -1.75 and -1.591 values between -1.59 and -1.442 values between -1.44 and -1.282 values between -1.28 and -1.122 values between -1.12 and -0.974 values between -0.97 and -0.816 values between -0.81 and -0.6515 values between -0.65 and -0.5018 values between -0.50 and -0.3473 values between -0.34 and -0.18437 values between -0.18 and -0.031614 values between -0.03 and 0.131223 values between 0.13 and 0.29409 values between 0.29 and 0.4475 values between 0.44 and 0.6015 values between 0.60 and 0.765 values between 0.76 and 0.911 values between 1.07 and 1.232 values between 1.23 and 1.381 values between 1.70 and 1.861 values between 3.27 and 3.421 values between 4.36 and 4.52offnegativepositiveoften

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. 因为他们
  2. ascript
  3. питания
  4. tics
  5. ibrate
  6. ervation
  7. cial
  8. خر
  9. 当前位置
  10. 农业大学

Suppresses

  1. ..."⏎⏎
  2. ..."⏎⏎
  3. lijk
  4. ...",
  5. 所
  6. ...',
  7. ENDED
  8. lu
  9. ...)⏎⏎
  10. "...