Neuron Explorer

Qwen3-0.6B

'even' after 'but' or 'while'

A neuron in layer 16 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

The neuron fires on the word 'even' when it comes in the middle of a sentence after words like 'But', 'while', or 'such', as in 'But even when you want to write'. Turning it up didn't produce a clear theme, so the model's replies were mostly unrelated.

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

    seeking war with Iran – No!), this is crazy. First, he’s advocating for homosexually-active men to enter fake marriages. This is defending marriage? But even better, let’s take a quick look at Alexander’s marriage policies, from Ar

  2. #2 peak

    Gilly Hopkins, like most of Paterson's novels for young adults, addresses the difficulty of growing up in an unpredictable world where even friendship and family cannot be taken for granted. Eleven-year-old Gilly Hopkins has

  3. #3 peak

    11<|endoftext|>For many people, writing text is an extremely painful process. It requires frankness and honesty, a lot of patience, and intellectual effort. But even when you want or need to write, you cannot. Looking at a blank slate

  4. #4 peak

    bytes) and the constant influx of new digital content poses a real challenge for archivists. Hard disks are expensive and require a constant supply of electricity, while even the best 'no-power' archiving materials such as magnetic tape degrade within a

  5. #5 peak

    The atmospheric concentration of ozone-depleting CFCs and halons has been falling since the adoption of the Montreal Protocol in 1987. But even as these chemicals have been phased out of aerosol cans, refrigerators, fire

  6. #6 peak

    weight.⏎- Would have a body weight that is 15% below than what is considered normal for age and height. They would refuse to maintain it such even after advice⏎- Be obsessed with body image and shape. They often fail to

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: what is the real meaning of it? it is a fact, but it's not sure that it is the right? but why, but why it's a fact, but why it's a fact? it is not sure? but why

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

    Struggle-For-Power-In-The-994323.html>.⏎"The Struggle for Power in the Ussr." StudyMode.com. 0<|endoftext|>Afghanistan and Colombia, half a world apart and different in culture

  2. #2 peak

    |The Physical Object|⏎|Number of Pages||136|⏎Learn why the Common Core is

  3. #3 peak

    of Principles of Biblical Interpretation found in the catalog.⏎April 1, 2003⏎by Baker Academic⏎Written in English⏎|The Physical Object|⏎|Number of Pages||180|⏎Hermeneutics gives

  4. #4 peak

    this past summer.⏎Complete information about survivors could not be confirmed<|endoftext|>A simple example of HTML is:⏎<HTML> <HEAD> <TITLE>This is the Title</TITLE> </HEAD> <BODY

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. L4:661 excites
  2. L4:1949 suppresses
  3. L4:3039 excites
  4. L10:652 weakly suppresses
  5. L11:1205 weakly suppresses
  6. L15:238 weakly excites
  7. L15:651 weakly suppresses
  8. L10:2876 weakly excites
  9. L14:1940 weakly excites
  10. L15:1095 weakly suppresses
  11. L9:880 weakly suppresses
  12. L14:2543 weakly suppresses
  13. L12:602 weakly excites
  14. L6:275 weakly excites
  15. L2:2839 weakly excites
  16. L4:1209 weakly suppresses
  17. L15:451 weakly excites
  18. L6:2217 weakly excites
  19. L11:2273 weakly suppresses
  20. L15:740 weakly excites
  21. L14:1930 weakly suppresses
  22. L13:11 weakly suppresses
  23. L11:1213 weakly excites
  24. L13:2520 weakly excites

Feeds later layers

  1. L18:1130 excites
  2. L17:1995 excites
  3. L20:458 excites
  4. L19:1590 excites
  5. L18:1915 excites
  6. L17:39 weakly excites
  7. L24:148 weakly excites
  8. L24:116 weakly suppresses
  9. L27:3043 weakly suppresses
  10. L19:832 weakly suppresses
  11. L18:598 weakly suppresses
  12. L22:1633 weakly suppresses
  13. L24:2464 weakly excites
  14. L22:1067 weakly suppresses
  15. L19:1793 weakly suppresses
  16. L17:1596 weakly excites
  17. L26:1661 weakly suppresses
  18. L22:571 weakly suppresses
  19. L19:800 weakly suppresses
  20. L17:2902 weakly suppresses
  21. L17:2801 weakly suppresses
  22. L18:2138 weakly suppresses
  23. L17:1027 weakly suppresses
  24. L19:1689 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.

333 values between -0.92 and -0.403271 values between -0.40 and 0.11239 values between 0.11 and 0.6312 values between 0.63 and 1.1413 values between 1.14 and 1.663 values between 1.66 and 2.175 values between 2.17 and 2.685 values between 2.68 and 3.203 values between 3.20 and 3.713 values between 3.71 and 4.232 values between 4.23 and 4.743 values between 4.74 and 5.262 values between 5.26 and 5.771 values between 6.28 and 6.801 values between 7.31 and 7.831 values between 8.86 and 9.371 values between 9.88 and 10.401 values between 10.40 and 10.911 values between 10.91 and 11.431 values between 11.94 and 12.461 values between 12.46 and 12.971 values between 14.00 and 14.511 values between 14.51 and 15.031 values between 15.54 and 16.061 values between 16.06 and 16.571 values between 18.63 and 19.141 values between 19.14 and 19.66offnegativepositiveoften

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. unge
  2. &P
  3. éré
  4. 在过渡
  5. ��
  6. ighet
  7. prs
  8. aced
  9. >Password
  10. isseur

Suppresses

  1. 又
  2. IELD
  3. arious
  4. course
  5. orrh
  6. 又称
  7. often
  8. щин
  9. 有多大
  10. ines