Neuron Explorer

Qwen3-0.6B

'and' joining the last item in a list

A neuron in layer 3 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

It fires on the word 'and' when it comes just before the final item of a list, such as 'produce, export, and import'. It is weakly active there and turns strongly off at the start of a new document. Turning it up did not produce a clear visible change.

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

    from the knee) (Figure 2).⏎Angular Limb Deviations are usually easily diagnosed by looking at the limbs standing directly in front of, directly behind, and/or from the side of the foal. You can also observe the foal

  2. #2 peak

    their third annual "IBM Next Five in Five" includes a mention of solar power. The list includes five innovations that will change the way people work, live, and play over the next five years. Accordingly, IBM thinks energy saving solar technology will

  3. #3 peak

    in Proceedings of the National Academy of Sciences.⏎A major challenge for tissue engineering is to identify the essential environmental ingredients that cells need in order to communicate, migrate, and organize into living tissues. One of these ingredients is the presence, outside the cell

  4. #4 peak

    consequences for people and society.⏎In this report, the Ada Lovelace Institute explores the datafication of health: what it is, how it occurs, and its impacts on individual and social wellbeing. We draw on examples to synthesise existing

  5. #5 peak

    finding any old stick to bash natural gas with is that nations will burn coal instead. Or just ignore the zealots and move forward rapidly to produce, export, and import methane. While Canada’s elite stands there slack-jawed going but what

  6. #6 peak

    lot of talk over the last several years about the nutrition of school meals – where the ingredients come from, how they’re prepared, what the food tastes like, and how the meal is presented. These are all important conversations for elevating the quality

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: I don't have the same experience as the people who are in the same situation as me. I don't have the same experience as the people who are in the same situation as me. I don't have the same experience as the people

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

    <|endoftext|>Cancer & Tumorigenesis⏎Cancer describes the disease with uncontrolled

  2. #2 peak

    Li<|endoftext|>What was the role of residential segregation in enabling the racial wealth gap? Why does the

  3. #3 peak

    <|endoftext|>Charles Messier (France) had just completed an observation of Jupiter and was in the

  4. #4 peak

    <|endoftext|>Public holidays in Pakistan are different than bank holidays in the country. While all of the

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. L2:210 strongly excites
  2. L2:1021 excites
  3. L2:246 excites
  4. L2:36 excites
  5. L2:1899 excites
  6. L2:839 excites
  7. L2:602 suppresses
  8. L2:112 excites
  9. L2:175 excites
  10. L2:2242 suppresses
  11. L2:1710 suppresses
  12. L2:234 excites
  13. L2:503 suppresses
  14. L2:165 excites
  15. L2:86 suppresses
  16. L2:1578 excites
  17. L2:356 excites
  18. L2:111 suppresses
  19. L2:305 suppresses
  20. L2:637 suppresses
  21. L2:216 excites
  22. L2:989 suppresses
  23. L2:28 suppresses
  24. L2:854 excites

Feeds later layers

  1. L6:24 excites
  2. L5:187 suppresses
  3. L6:208 suppresses
  4. L15:306 suppresses
  5. L6:277 suppresses
  6. L6:374 excites
  7. L6:212 weakly excites
  8. L11:539 weakly suppresses
  9. L6:22 weakly excites
  10. L7:241 weakly excites
  11. L6:14 weakly excites
  12. L4:10 weakly excites
  13. L11:1353 weakly excites end-of-document token after a web snippet
  14. L10:859 weakly excites unclear: word fragments, weak
  15. L6:70 weakly excites
  16. L6:34 weakly excites
  17. L18:388 weakly suppresses
  18. L5:195 weakly excites
  19. L9:1524 weakly excites
  20. L19:1676 weakly suppresses
  21. L8:56 weakly excites
  22. L26:1564 weakly excites
  23. L12:114 weakly suppresses
  24. L6:879 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 -2.23 and -2.161 values between -2.01 and -1.942 values between -1.05 and -0.981 values between -0.90 and -0.832 values between -0.83 and -0.761 values between -0.76 and -0.682 values between -0.54 and -0.463 values between -0.46 and -0.3913 values between -0.31 and -0.2451 values between -0.24 and -0.17228 values between -0.17 and -0.09680 values between -0.09 and -0.021245 values between -0.02 and 0.06931 values between 0.06 and 0.13497 values between 0.13 and 0.20161 values between 0.20 and 0.2854 values between 0.28 and 0.3519 values between 0.35 and 0.438 values between 0.43 and 0.506 values between 0.50 and 0.571 values between 0.57 and 0.651 values between 0.65 and 0.72offnegativepositiveoften

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. idades
  2. itous
  3. izo
  4. .microsoft
  5. ochond
  6. ilde
  7. angelog
  8. ypress
  9. ��
  10. ipients

Suppresses

  1. herself
  2. 她说
  3. 像是
  4. 一件事情
  5. 她是
  6. 那个人
  7. 某个
  8. \Id
  9. oneself
  10. 一艘