Neuron Explorer

Qwen3-0.6B

line break in the middle of a sentence

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

This neuron fires on a line break that cuts a sentence in two, where the text carries on onto the next line, as in 'over the last / six years'. It is quiet, or slightly negative, when a line break follows a full stop or a comma that ends a sentence or item.

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

    impaired people.⏎Over the last⏎six years, FNB have been at the forefront of making information⏎accessible for

  2. #2 peak

    Cooper.⏎Buy the hardcover edition of⏎I Heard the Willow Weep for $6.00. (Retail price

  3. #3 peak

    think⏎- Sharing knowledge and reasoning⏎- Reflecting and making use of what has been said⏎- Coming to a consensus⏎You will be working in a⏎team of four. Ensure that you have plenty of cubes. Their colour⏎does

  4. #4 peak

    QRcode is below.⏎Features of QRcode are⏎QRcode model1:Original model.⏎QRcode model2:Extended model.⏎

  5. #5 peak

    statement that increases count if a given number is found.⏎Type your code here:⏎See your results here:⏎Start with the code here that initializes the variable count to⏎zero, then runs the variable num from 1 to 999 (

  6. #6 peak

    it is not necessary to know it,⏎but in some cases the difference between shared and separated objects yields different orders of space or time complexity.⏎Consider the infinite list⏎let x =

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 need to get to the point of a different question, but I need to ask for help in a different way. So I have to ask for help. I am going to get the point of a different question. But 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

    . Kilda Cemetery), Alfred Felton (St.⏎Kilda Cemetery) of “Felton, Grimwade & Co”, and Alfred Deakin (St.⏎Kilda Cemetery), thrice Prime Minister of Australia. Residing at 7

  2. #2 peak

    shape or speed. Solitary waves occur in the atmosphere elsewhere, says Jorg⏎Hacker, of Airborne Research Australia in Adelaide. They are usually invisible,⏎however, because they carry no cloud. "But in the Gulf, the humidity

  3. #3 peak

    true in some scenarios, the program did build some advantages for the future.⏎The ALTB is an aircraft with a direct energy laser. It was developed to identify, track, and shoot down enemy ballistic missiles during the most vulnerable boost phase of flight

  4. #4 peak

    craft glows during its atmospheric re-entry, in a view⏎captured Monday from a DC-8 observation plane flying over the Pacific. A lens⏎diffraction flare can be seen in rainbow colors at lower right.⏎Today's first

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. L2:593 weakly suppresses
  2. L2:156 weakly suppresses
  3. L2:225 weakly excites
  4. L2:236 weakly suppresses
  5. L2:139 weakly excites
  6. L2:2312 weakly excites
  7. L1:116 weakly excites
  8. L2:2432 weakly suppresses
  9. L0:3063 weakly suppresses
  10. L2:2553 weakly suppresses
  11. L2:894 weakly excites
  12. L2:71 weakly suppresses
  13. L1:1076 weakly suppresses
  14. L1:1450 weakly suppresses
  15. L1:1478 weakly suppresses
  16. L1:246 weakly suppresses comma after an introductory time phrase
  17. L0:2 weakly suppresses
  18. L2:996 weakly suppresses
  19. L2:883 weakly excites
  20. L2:888 weakly suppresses
  21. L2:1706 weakly suppresses
  22. L1:1 weakly excites
  23. L2:1332 weakly excites
  24. L2:652 weakly suppresses

Feeds later layers

  1. L7:288 weakly excites
  2. L4:863 weakly excites
  3. L5:460 weakly excites
  4. L9:458 weakly excites
  5. L7:613 weakly excites
  6. L7:802 weakly excites
  7. L15:1361 weakly suppresses
  8. L5:168 weakly suppresses
  9. L23:2470 weakly suppresses
  10. L10:2413 weakly excites
  11. L5:1029 weakly excites
  12. L4:105 weakly excites
  13. L24:1133 weakly excites
  14. L10:819 weakly excites
  15. L17:1906 weakly excites
  16. L12:2507 weakly suppresses
  17. L7:1006 weakly excites
  18. L11:254 weakly suppresses
  19. L11:1210 weakly excites
  20. L5:454 weakly excites
  21. L24:2929 weakly suppresses
  22. L16:1565 weakly excites
  23. L13:1532 weakly excites
  24. L12:1602 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 -2.22 and -2.111 values between -2.00 and -1.901 values between -1.58 and -1.481 values between -1.16 and -1.062 values between -1.06 and -0.952 values between -0.85 and -0.745 values between -0.74 and -0.6414 values between -0.64 and -0.5323 values between -0.53 and -0.4362 values between -0.43 and -0.32129 values between -0.32 and -0.22315 values between -0.22 and -0.111167 values between -0.11 and -0.001660 values between -0.00 and 0.10349 values between 0.10 and 0.21106 values between 0.21 and 0.3130 values between 0.31 and 0.4210 values between 0.42 and 0.5211 values between 0.52 and 0.635 values between 0.63 and 0.732 values between 0.73 and 0.842 values between 0.84 and 0.941 values between 0.94 and 1.052 values between 1.05 and 1.151 values between 1.15 and 1.261 values between 1.26 and 1.361 values between 1.47 and 1.581 values between 1.58 and 1.683 values between 1.89 and 2.00offnegativepositiveoften

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. elian
  2. eel
  3. 网讯
  4. :\/\/
  5. רק
  6. cooked
  7. ippo
  8. '&#
  9. odon
  10. rzy

Suppresses

  1. dda
  2. acam
  3. اه
  4. INESS
  5. NESS
  6. ersistent
  7. ship
  8. ylvania
  9. ネ
  10. VES