Neuron Explorer

Qwen3-0.6B

unclear: scattered web and commerce text

A neuron in layer 11 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 weakly on a mix of ordinary words in shopping pages, school material and news, with no clear shared pattern. It is hard to say what it cares about, and turning it up did not reveal a theme.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

    .0400.025.SS UNSPSC Code 30260000 See more.Customers who bought this item also bought.Page 1 of 1 Start over Page 1 of 1 .

  2. #2 peak

    UP Details⏎Happy Homeschool Month! The whole month of January we will have NEW DEALS every week for you to stock up for the new year! Use code: STOCKUP at checkout to get an EXTRA 10% off sitew

  3. #3 peak

    a floor prototype of the brand new exploration extravehicular mobility unit (xEMU) in 2019 at NASA Headquarters in Washington. Credit score: Joel Kowsky/NASA⏎One of many principal elements is the cooling garment

  4. #4 peak

    of this warm-up is for students to reason about two objects that have the same volume but different surface areas within a context.⏎Give students 1 minute of quiet think time followed by a whole-class discussion.⏎Mai’s science teacher told her that

  5. #5 peak

    control the back and forth movement of the knee.⏎Most injuries to the ACL happen when playing sports, such as football, squash, tennis or skiing (see the box, left). ACL injuries account for 40% of all sports injuries.⏎

  6. #6 peak

    (in Central America)|⏎|Scientific Name||Lampropeltis triangulum gaigeae|⏎|Conservation Status||Not listed by IUCN|⏎When these snakes are young,

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 number of the last person in the "Bible" of the "Garden of Eden" to the number of the last person in the "Garden of Eden" on a single page. The number of "Bible" of

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

    forward to coming in every year to see me.⏎Holding space for someone is a big deal, and it doesn’t happen often. Think about it – how many times do you have an encounter with someone and feel their presence is open, attentive

  2. #2 peak

    Sen. Marshall. “The clock is ticking as parents inch closer to the fall semester and return their children to the classroom. Every parent and physician I’ve talked to has told me if they knew their patient or child’s level of immune response,

  3. #3 peak

    (through our fingertips) to electronic devices. And it isn’t as if the possibilities of neural interface technologies haven’t been considered, or even capitalized on (just ask Joss Whedon or the Wachowski brothers or Dr. Octopus

  4. #4 peak

    people and organizations try making sense of things.⏎Have rumors always existed in human history, or are they relatively modern?⏎I think they have always existed. You can find rumors in ancient writing, usually described as something you didn't want to listen to

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. L10:2960 suppresses
  2. L7:1562 excites
  3. L6:2883 excites
  4. L8:838 suppresses
  5. L7:2400 weakly excites
  6. L9:903 weakly suppresses
  7. L10:1371 weakly suppresses
  8. L7:2894 weakly excites
  9. L8:285 weakly excites
  10. L4:2789 weakly excites
  11. L8:2122 weakly excites hand and body action verbs in instructions
  12. L1:2853 weakly suppresses
  13. L10:3044 weakly suppresses
  14. L4:2258 weakly suppresses
  15. L8:2738 weakly excites
  16. L10:2643 weakly suppresses
  17. L5:1786 weakly excites
  18. L8:1609 weakly suppresses
  19. L8:1818 weakly excites
  20. L6:391 weakly suppresses
  21. L10:283 weakly excites
  22. L10:3056 weakly excites
  23. L10:1221 weakly excites
  24. L7:255 weakly excites

Feeds later layers

  1. L13:1954 suppresses
  2. L13:395 suppresses
  3. L15:2000 suppresses
  4. L14:436 excites
  5. L13:2319 excites
  6. L12:1525 excites
  7. L14:2472 suppresses
  8. L14:2429 weakly suppresses
  9. L15:2640 weakly suppresses
  10. L13:1184 weakly suppresses
  11. L14:2870 weakly excites
  12. L13:276 weakly suppresses
  13. L14:1604 weakly suppresses
  14. L13:1452 weakly suppresses
  15. L13:580 weakly suppresses
  16. L17:2645 weakly suppresses
  17. L13:2697 weakly suppresses
  18. L12:681 weakly suppresses
  19. L13:79 weakly suppresses
  20. L12:2825 weakly suppresses
  21. L15:997 weakly excites
  22. L16:2860 weakly suppresses
  23. L14:1206 weakly suppresses
  24. L17:2754 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 -2.86 and -2.751 values between -2.31 and -2.192 values between -1.75 and -1.641 values between -1.52 and -1.415 values between -1.41 and -1.304 values between -1.30 and -1.194 values between -1.19 and -1.0812 values between -1.08 and -0.9712 values between -0.97 and -0.8612 values between -0.86 and -0.7428 values between -0.74 and -0.6332 values between -0.63 and -0.5261 values between -0.52 and -0.4178 values between -0.41 and -0.30151 values between -0.30 and -0.19434 values between -0.19 and -0.071746 values between -0.07 and 0.04759 values between 0.04 and 0.15275 values between 0.15 and 0.26118 values between 0.26 and 0.3757 values between 0.37 and 0.4934 values between 0.49 and 0.6027 values between 0.60 and 0.7118 values between 0.71 and 0.8219 values between 0.82 and 0.937 values between 0.93 and 1.042 values between 1.04 and 1.154 values between 1.15 and 1.273 values between 1.27 and 1.381 values between 1.49 and 1.60offnegativepositiveoften

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. ựa
  2. othy
  3. Specialists
  4. ymm
  5. elyn
  6. пока
  7. nock
  8. etermin
  9. endors
  10. ,+

Suppresses

  1. scri
  2. chè
  3. 侄
  4. Patri
  5. ched
  6. 相近
  7. 书籍
  8. ="#"><
  9. íst
  10. }`,