Neuron Explorer

Qwen3-0.6B

'be' after 'might', 'also' or 'only'

A neuron in layer 1 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 word 'be' when it comes after words like 'might', 'also', 'only' or 'can't', as in 'you might also be interested'. Steering did not show a clear, consistent change in the text.

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

    cover creating a 90 degree pipe that goes with the T-Section pipe we created in the Creating A Simple Mesh Using Splines tutorial.⏎I will only be introducing one

  2. #2 peak

    ⏎, focuses on Earth System science, including articles on student inquiry, differentiated instruction, geomorphic concepts, the rock cycle, and much more!⏎You might also be interested in:⏎About 70<|endoftext|>- freely available⏎Int. J.

  3. #3 peak

    others. Arid, desert climates have much less humidity and homes may need to be supplemented with a humidifier to make the air moister.⏎You might actually be the one responsible for frequent nose bleeds. Bad habits such as nose-picking

  4. #4 peak

    adequate resources: If a school doesn’t have enough funds to manage computers equal to number of students, trust me the idea will fail badly. Obviously you can’t be wasting the precious time of students getting them in turns to use the computers and requiring

  5. #5 peak

    disease,'' said Jack, echoing the opinion of the other 15 boys at the experimental Aspie school here in the Catskills. ''So we can't be 'cured.' This is just the way we are.''⏎From behind his

  6. #6 peak

    ots from forming.⏎Anti-platelet drugs are given to someone who has had a heart attack, to reduce the chances of them having another. You might also be given anti-platelets if you have had a stent fitted to a narrowed

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 can't be too much. I have to be a very small part of the whole. So, I need to be able to be a very small part of the whole. I can't be too much. So, I need to

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

    + 314⏎Are the denominators equivalent? Yes, they are.⏎Now we can add the cardinal numbers and the numerators. First the cardinal

  2. #2 peak

    parent graph of cotangent, cot x in the figure.<|endoftext|>The steps are shown in IIS 10 on Windows 10 Enterprise, but they are also shown in IIS

  3. #3 peak

    which seems to be unique in the Indo<|endoftext|>A POTENTIALLY deadly and virulent bug that

  4. #4 peak

    Mats⏎These free blank alphabet letter mats make look simple, but they are filled with possibility for your preschool classroom! Blank ABC letters can be filled with a

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. L0:2560 weakly excites
  2. L0:1518 weakly excites
  3. L0:2869 weakly excites
  4. L0:2893 weakly suppresses
  5. L0:2803 weakly excites
  6. L0:2322 weakly excites
  7. L0:537 weakly suppresses the 'or' in 'and/or'
  8. L0:1224 weakly suppresses
  9. L0:2360 weakly excites
  10. L0:827 weakly excites
  11. L0:1183 weakly suppresses
  12. L0:1190 weakly excites
  13. L0:437 weakly excites
  14. L0:1615 weakly excites
  15. L0:912 weakly suppresses
  16. L0:2808 weakly suppresses
  17. L0:1587 weakly suppresses
  18. L0:2054 weakly excites
  19. L0:678 weakly excites
  20. L0:273 weakly suppresses
  21. L0:2463 weakly suppresses
  22. L0:2454 weakly excites
  23. L0:178 weakly suppresses
  24. L0:122 weakly excites

Feeds later layers

  1. L9:1248 excites
  2. L20:386 excites
  3. L5:17 excites
  4. L15:2783 suppresses
  5. L21:1122 weakly suppresses
  6. L3:361 weakly excites
  7. L23:2537 weakly suppresses
  8. L15:576 weakly excites
  9. L21:1259 weakly suppresses
  10. L25:478 weakly suppresses
  11. L21:618 weakly suppresses
  12. L12:2824 weakly suppresses
  13. L13:971 weakly excites
  14. L3:185 weakly suppresses
  15. L12:2608 weakly excites
  16. L2:940 weakly excites
  17. L9:3002 weakly suppresses
  18. L4:918 weakly suppresses
  19. L12:912 weakly excites
  20. L8:2549 weakly excites
  21. L17:1783 weakly suppresses
  22. L7:1735 weakly suppresses
  23. L8:2674 weakly excites
  24. L3:728 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 -2.21 and -2.101 values between -1.98 and -1.871 values between -1.63 and -1.521 values between -1.52 and -1.401 values between -1.40 and -1.291 values between -1.29 and -1.172 values between -1.17 and -1.053 values between -1.05 and -0.945 values between -0.94 and -0.825 values between -0.82 and -0.719 values between -0.71 and -0.598 values between -0.59 and -0.4717 values between -0.47 and -0.3666 values between -0.36 and -0.24300 values between -0.24 and -0.131356 values between -0.13 and -0.011805 values between -0.01 and 0.11254 values between 0.11 and 0.2248 values between 0.22 and 0.346 values between 0.34 and 0.453 values between 0.45 and 0.576 values between 0.57 and 0.694 values between 0.92 and 1.031 values between 1.03 and 1.152 values between 1.50 and 1.611 values between 1.61 and 1.731 values between 2.31 and 2.43offnegativepositiveoften

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. istics
  2. _CASE
  3. _ROUT
  4. 一群人
  5. _MISSING
  6. 我的心
  7. arer
  8. 口中
  9. 的需求
  10. 说我

Suppresses

  1. cka
  2. achable
  3. acre
  4. shortened
  5. emo
  6. аниз
  7. นำไป
  8. icks
  9. segment
  10. uda