Neuron Explorer

Qwen3-0.6B

unclear: conjunctions after a clause

A neuron in layer 16 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 on small connecting words like 'as long as', 'although', 'however' and 'unless the', right where a sentence is about to add a qualifier or contrast. When turned up, the output drifted into rambling, looping text with no clear theme.

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

    , physicists have been on the hunt for gravitational waves, ripples in the fabric of spacetime. That hunt is now over. Gravitational waves exist, and we’ve found them.⏎That’s according to researchers at the Laser Interferometer

  2. #2 peak

    a conversation” or a “description of a feature”. (A BDD story can just as easily describe a non-functional requirement, as long as the work can be scoped, estimated and agreed on.)⏎The structure of a story

  3. #3 peak

    of physical contact, while 40% reported experiencing verbal abuse.⏎The problem is not limited to female students, however. Male students also experience sexual harassment, although to a lesser extent. According to the same study, 20% of

  4. #4 peak

    can be made with just about any verb: to do, to be, to go, to make, to take, to see, to get–as long as you use the simple form of the verb. Infinitives can’t be used

  5. #5 peak

    children are influenced by the behavior of adults, use of electronics by adults is discouraged at Cub Scout meetings and events unless the activity requires the use of them or unless the adult is taking pictures of the event.⏎We understand that many adults have jobs that

  6. #6 peak

    you). As an Amazon Associate I earn from qualifying purchases. Please read my disclaimer for additional details.⏎Can goats eat strawberries?⏎Yes, goats can eat strawberries, however, not all goats are fond of their sour and sweet taste. Strawberries consist

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 128.128.152.155? I know my computer...? What is the...? I need something? And what is the 128...?

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

    with relevant visual imagery.⏎3 Steps to Creating an Awesome Virtual Museum in Class You're spending an afternoon browsing the exhibits at an art museum. If you're anything like me, you'd probably appreciate the art a lot more if you could bring someone

  2. #2 peak

    evolve as musicians and songwriters and subsequently engineer a truly global revolution in an exhilarating short period<|endoftext|>It's natural for your brain to age over time, just like the rest of your body. However, your diet and lifestyle can also impact the

  3. #3 peak

    (GNBDK)⏎Never do to anyone else anything that you would not want someone to do to you. “Do not drink so much wine that you get

  4. #4 peak

    the famous and prestigious Eleven Towns Race that takes place in his country. For years Piet has dreamed of proving that he is a skater as brave and strong as Pim Mulier -- but he had never imagined that his test would fall under

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. L14:1891 excites
  2. L15:1702 excites
  3. L15:1068 suppresses
  4. L14:531 suppresses
  5. L14:2150 excites
  6. L14:655 excites
  7. L12:896 suppresses
  8. L6:2699 excites
  9. L11:3015 suppresses
  10. L6:502 suppresses
  11. L12:2215 excites 'of' after 'one' or 'some' (partitives)
  12. L13:2401 suppresses
  13. L14:2861 excites 'of' after a percentage
  14. L14:1128 excites
  15. L12:1653 suppresses
  16. L14:778 excites
  17. L15:1226 suppresses
  18. L12:2440 suppresses
  19. L1:1369 suppresses
  20. L15:1310 excites
  21. L7:751 weakly suppresses
  22. L14:1340 weakly excites
  23. L14:2739 weakly excites
  24. L15:931 weakly excites

Feeds later layers

  1. L17:2749 suppresses
  2. L17:865 weakly suppresses
  3. L17:57 weakly suppresses
  4. L17:441 weakly excites
  5. L24:2586 weakly suppresses
  6. L19:2671 weakly excites
  7. L18:773 weakly excites
  8. L17:2352 weakly suppresses
  9. L18:2997 weakly suppresses
  10. L17:201 weakly suppresses
  11. L17:458 weakly suppresses
  12. L19:1024 weakly suppresses
  13. L19:1617 weakly suppresses
  14. L24:2831 weakly suppresses
  15. L19:1563 weakly suppresses
  16. L17:1058 weakly suppresses
  17. L19:605 weakly suppresses
  18. L23:238 weakly suppresses
  19. L19:1778 weakly excites
  20. L17:775 weakly suppresses
  21. L19:669 weakly suppresses
  22. L20:1977 weakly suppresses
  23. L18:552 weakly excites
  24. L17:862 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 -5.40 and -5.162 values between -3.70 and -3.452 values between -2.96 and -2.721 values between -2.72 and -2.482 values between -2.48 and -2.231 values between -2.23 and -1.992 values between -1.99 and -1.748 values between -1.74 and -1.509 values between -1.50 and -1.268 values between -1.26 and -1.0119 values between -1.01 and -0.7755 values between -0.77 and -0.52145 values between -0.52 and -0.281038 values between -0.28 and -0.042109 values between -0.04 and 0.21326 values between 0.21 and 0.4579 values between 0.45 and 0.7038 values between 0.70 and 0.9417 values between 0.94 and 1.1819 values between 1.18 and 1.4310 values between 1.43 and 1.676 values between 1.67 and 1.924 values between 1.92 and 2.161 values between 2.16 and 2.401 values between 2.40 and 2.652 values between 2.65 and 2.891 values between 2.89 and 3.141 values between 3.62 and 3.871 values between 4.11 and 4.36offnegativepositiveoften

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. pics
  2. HttpServletRequest
  3. quisitions
  4. 刑
  5. pert
  6. \Column
  7. ;]/
  8. _CID
  9. RL
  10. paj

Suppresses

  1. 儿子
  2. odon
  3. ankan
  4. nty
  5. arter
  6. Atom
  7. adget
  8. plitude
  9. side
  10. sons