Neuron Explorer

Qwen3-0.6B

end-of-text token after a finished passage

A neuron in layer 18 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 invisible end-of-document marker that appears right after a passage stops, where the next text is unrelated. Pushing it up made the model drift into unrelated topics.

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

    manage operations in your warehouse.⏎- Lay out a proper strategy for handling damaged products and returns from customers.⏎- Implement pest control measures to protect your products.⏎-<|endoftext|>Nucleation properties of respirable coal dust (terminal progress report).⏎Physics Department

  2. #2 peak

    be the most effective approach. Smart work, on the other hand, can save time and increase productivity, but may lead to a lack of focus on the details<|endoftext|>Rajan Vempati of ChK Group, Inc. in Plano,

  3. #3 peak

    ), Applying the ecosystem approach (Section 3), creating a management plan (Section 4) and assessing a project against the ecosystem approach (Section 5).<|endoftext|>We offer free Maharashtra

  4. #4 peak

    1, on the Mall in front of the National Air and Space Museum. The museum will also be hosting a scholarly conference on Civil War ballooning on June <|endoftext|>Most veteran peanut farmers in the Southeast will remember the devastating spread of tomato spotted wilt

  5. #5 peak

    students into groups of three.⏎Allow time for all three group members to be traced. Students may then complete⏎silhouettes at home or during free time.<|endoftext|>2010 is the International Year of Biodiversity. Why should you

  6. #6 peak

    be considered a planet, reigniting discussions.⏎In<|endoftext|>The Carnival season, or “Apokries” in Greek, is slowly coming

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 first of the years of the first of the years. I think that this is a good idea, if we can find the first of the first of the first. This is a very small step. is a small step. The first

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

    920 by the Nineteenth Amendment to the federal Constitution, the...⏎Users without a subscription are not able to see the full⏎to access all content.<|endoftext|>Great Slaty becomes World's Largest Woodpecker as Ivory Billed

  2. #2 peak

    12|⏎|Journal||Classical and Quantum Gravity|⏎|State||Published - Jul 7 2003|⏎ASJC Scopus subject areas⏎- Physics and Astronomy (miscellaneous)<|endoftext|>Most computer users are familiar with the

  3. #3 peak

    silkworm-BEVS is a promising alternative strategy to produce the functional and thermostable reverse transcriptase.⏎All Science Journal Classification (ASJC) codes⏎- Insect Science<|endoftext|>An account of the religion of

  4. #4 peak

    show us God’s glory and sovereignty, and so others will believe on him.⏎Leave your comments below to share your thoughts on the subject. If you think others would appreciate reading this, please share it through the social media

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. L17:658 strongly suppresses
  2. L16:235 strongly suppresses
  3. L17:3036 strongly excites end of document boundary
  4. L16:2524 strongly excites
  5. L17:1088 excites
  6. L15:1246 suppresses
  7. L15:2977 suppresses
  8. L15:2544 suppresses
  9. L15:2675 excites
  10. L15:101 excites
  11. L15:917 suppresses
  12. L15:2249 excites
  13. L12:2927 suppresses
  14. L15:1567 suppresses
  15. L15:774 excites
  16. L16:2772 excites
  17. L16:1411 excites
  18. L9:1039 excites
  19. L16:2510 excites
  20. L13:2897 excites
  21. L17:1523 suppresses
  22. L10:1298 excites
  23. L17:2723 excites
  24. L15:131 suppresses

Feeds later layers

  1. L19:2057 strongly suppresses
  2. L26:2128 strongly suppresses decimal points inside numbers
  3. L22:417 suppresses period closing a web blurb
  4. L25:808 suppresses
  5. L20:338 suppresses
  6. L24:736 suppresses
  7. L21:1150 excites
  8. L27:725 suppresses
  9. L19:1069 suppresses
  10. L21:301 excites
  11. L22:552 suppresses
  12. L20:309 suppresses
  13. L19:301 suppresses
  14. L19:1105 weakly excites
  15. L26:449 weakly excites
  16. L24:211 weakly excites
  17. L26:288 weakly excites
  18. L19:1527 weakly suppresses
  19. L20:460 weakly excites
  20. L19:2031 weakly suppresses line breaks in web footers and metadata
  21. L26:16 weakly suppresses
  22. L24:36 weakly excites
  23. L20:44 weakly excites
  24. L22:91 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 -8.78 and -8.401 values between -6.86 and -6.481 values between -5.71 and -5.331 values between -5.33 and -4.941 values between -4.94 and -4.561 values between -4.56 and -4.173 values between -3.40 and -3.024 values between -3.02 and -2.644 values between -2.64 and -2.256 values between -2.25 and -1.8710 values between -1.87 and -1.4812 values between -1.48 and -1.1023 values between -1.10 and -0.7223 values between -0.72 and -0.3380 values between -0.33 and 0.052106 values between 0.05 and 0.441401 values between 0.44 and 0.82213 values between 0.82 and 1.2112 values between 1.21 and 1.591 values between 1.59 and 1.971 values between 2.36 and 2.741 values between 3.13 and 3.511 values between 4.66 and 5.051 values between 6.20 and 6.58offnegativepositiveoften

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. ';⏎⏎
  2. ":⏎⏎
  3. _);⏎⏎
  4. _;⏎⏎
  5. $⏎⏎
  6. лиц
  7. /";⏎⏎
  8. ':⏎⏎
  9. uko
  10. ksen

Suppresses

  1. <|endoftext|>
  2. enu
  3. 返回搜狐
  4. سب
  5. firstname
  6. firstname
  7. </
  8. ']?>"
  9. token
  10. }`