Neuron Explorer

Qwen3-0.6B

'and' or 'or' in split hyphen compounds

A neuron in layer 14 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 lights up on the word 'and' or 'or' when it comes right after a hyphenated prefix, as in 'short-and long-term' or 'mis-and dis-information'. The steering test gave rambling, unrelated text, so it does not show a clear effect on writing.

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

    curb would be difficult, if not impossible to do without the ability to maintain single limb support for a given amount of time. The ability to switch from two- to one-leg standing is required to perform turns, climb stairs and dress.⏎As we

  2. #2 peak

    of text. (Buzzfeed produced a helpful catalogue of all the fabricated and misleading stories distributed online.)⏎Visuals are regularly being used as persuasive vehicles for mis- and dis-information. And photographs are not the only kind of visuals to consider. Graph

  3. #3 peak

    getting organized. It offers tips for setting short- and long-term goals, choosing activities and fitting them into your daily life, and managing

  4. #4 peak

    several days, foraging movements confirmed by simultaneous acoustic observations of prey-sized fauna, movements parallel to the shore, and traveling between FADs. This intra- and inter-individual variety of behaviour might depend on the

  5. #5 peak

    the amount of random error involved in measuring student performance. The risk is that teachers and schools may be wrongfully rewarded or punished because value-added techniques either over- or underestimated their students’ learning gains. However, no intelligent users of standardized testing would

  6. #6 peak

    autopsies at 45 months. The effects of SIP forms on micro- and macrocell corrosion of reinforcement were investigated by statistically comparing the performance of specimens with and

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 have a 2000000000000000000001, which is 1,0000000000000000

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

    ||Environmental management|⏎Class 10 Science Chapter 4 Environmental management questions answers in Pdf format:⏎Here is what you all are waiting for. Teachers, parents and student, now you will find below the Solutions of Class 10 Science Chapter

  2. #2 peak

    ⏎Lin CC, Lin XM, Zou Y, Zhang L (2005) Study on the relationship between meteorological conditions

  3. #3 peak

    virus associated with multiple sclerosis⏎Science | January 13, 2022⏎Bjornevik K, Cortese M, Healy BC, Kuhle J, Mina MJ, Leng Y, Elledge SJ

  4. #4 peak

    your medicine is not helping or if you have side effects. Tell him or her if you are allergic to any medicine. Keep a list of the medicines, vitamins, and herbs you take. Include the amounts, and when and why you take them

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. L10:2046 suppresses
  2. L7:1382 suppresses
  3. L7:616 excites
  4. L10:338 weakly suppresses
  5. L13:1548 weakly excites
  6. L9:2244 weakly excites
  7. L13:615 weakly suppresses
  8. L2:747 weakly suppresses
  9. L4:1846 weakly suppresses
  10. L12:372 weakly suppresses
  11. L13:876 weakly excites
  12. L9:92 weakly suppresses "and" or "or" joining two items
  13. L1:1678 weakly excites
  14. L7:737 weakly suppresses comma after a place name
  15. L11:807 weakly suppresses
  16. L9:1449 weakly suppresses
  17. L9:940 weakly suppresses
  18. L7:391 weakly excites 'of' after 'those' or 'many'
  19. L7:2996 weakly excites
  20. L3:182 weakly suppresses
  21. L13:499 weakly suppresses
  22. L12:2458 weakly suppresses
  23. L7:173 weakly excites
  24. L7:2588 weakly excites

Feeds later layers

  1. L15:2239 suppresses
  2. L15:1475 suppresses
  3. L15:1230 suppresses
  4. L16:2199 excites
  5. L18:745 weakly excites
  6. L15:1653 weakly excites
  7. L19:1092 weakly excites
  8. L15:631 weakly suppresses
  9. L15:2642 weakly suppresses
  10. L26:1257 weakly excites
  11. L26:112 weakly suppresses
  12. L15:1260 weakly suppresses
  13. L16:1812 weakly suppresses
  14. L20:2262 weakly suppresses
  15. L18:2278 weakly excites
  16. L24:748 weakly excites
  17. L15:3057 weakly excites
  18. L15:2923 weakly excites
  19. L18:573 weakly suppresses
  20. L15:2169 weakly excites
  21. L25:1673 weakly excites
  22. L24:407 weakly excites
  23. L17:1400 weakly excites
  24. L16:2531 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.

2 values between -1.71 and -1.525 values between -1.52 and -1.333 values between -1.33 and -1.154 values between -1.15 and -0.964 values between -0.96 and -0.789 values between -0.78 and -0.5926 values between -0.59 and -0.40290 values between -0.40 and -0.221277 values between -0.22 and -0.031750 values between -0.03 and 0.16444 values between 0.16 and 0.3466 values between 0.34 and 0.537 values between 0.53 and 0.716 values between 0.71 and 0.903 values between 0.90 and 1.093 values between 1.09 and 1.271 values between 1.27 and 1.462 values between 1.46 and 1.641 values between 1.64 and 1.831 values between 1.83 and 2.021 values between 2.20 and 2.391 values between 2.95 and 3.131 values between 3.32 and 3.511 values between 5.55 and 5.74offnegativepositiveoften

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. ulet
  2. otive
  3. füg
  4. ью
  5. ometimes
  6. وس
  7. нд
  8. rooms
  9. icial
  10. שות

Suppresses

  1. waves
  2. 支持力度
  3. ante
  4. =”
  5. 性疾病
  6. “At
  7. ância
  8. _HandleTypeDef
  9. anza
  10. akukan