Neuron Explorer

Qwen3-0.6B

opening parenthesis after copyright or year

A neuron in layer 9 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 lights up on the open bracket that comes right before a year in citations and copyright lines, like 'Copyright (c) 2009'. Turning it up made the model's text drift into loose, unrelated talk; the steering is not clearly connected to this pattern.

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

    water, were the major factors shaping phytoplankton communities.⏎- Abstract views: 1777⏎- PDF: 842⏎Copyright (c) 2009 Silvia TAVERNINI, Daniele N

  2. #2 peak

    of creating a “thermostatic mechanism” that would counter-balance the dominant presence of electronic media in the lives of children.⏎How to Cite⏎Copyright (c) 2017 Robert Albrecht⏎Copyrights and publishing

  3. #3 peak

    ||Classical and Quantum Gravity|⏎|State||Published - Jul 7 2003|⏎ASJC Scopus subject areas⏎- Physics and Astronomy (miscellaneous)<|endoftext|>Most computer users are familiar with the concept of spyware —

  4. #4 peak

    icide and Social Change in China⏎- Cite this article as:⏎- Phillips, M.R., Liu, H. & Zhang, Y. Cult Med Psychiatry (1999) 23: 25. doi:1

  5. #5 peak

    viable. A symbol or instrument found in the Tuturangiana Andala ritual of green bamboo, betel nut, black goat, and red flag.⏎Copyright (c) 2022 Proceedings Of International Conference On Communication Science⏎This

  6. #6 peak

    . Ben Cohen. "The Racial Geography of the Federal Death Penalty" Washington Law Review (2010).<|endoftext|>Last updated 2/27/15

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: the need for a more sustainable energy policy, like the green energy transition, and the push for climate action to reduce emissions from carbon taxes, and the Paris climate goals, like the 2030 targets to combat climate change), the

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

    can contribute to the recovery of butterfly populations, although there is a paucity of information on the long-term effects of management. Using eight UK data sets (9–21 years), we investigate changes in restoration success for (1)

  2. #2 peak

    .⏎Climate change will disproportionately affect California’s most disadvantaged and isolated communities, according to a recent report from the Pacific Institute.⏎By looking at a broad array of factors – from social indicators such as income and birth rates, to environmental ones such as tree

  3. #3 peak

    ology for hints that the Red Planet may have ever had conditions hospitable to life.⏎The startlingly clear photo, one of several new views released by NASA today (Aug. 8), shows Curiosity's heat shield after it was shed about

  4. #4 peak

    in 1880. William Sutherland was one of several Scots who explored the country in the 19th century. He ended a wandering life (he had earlier fought under Garibaldi in Italy) when he settled at Mil

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. L5:330 excites opening parenthesis after a noun
  2. L8:354 excites opening parenthesis before a citation year
  3. L7:582 suppresses
  4. L3:57 excites
  5. L6:2715 suppresses
  6. L5:1130 excites
  7. L6:1295 suppresses
  8. L7:2445 suppresses
  9. L5:1682 weakly suppresses
  10. L6:1412 weakly suppresses
  11. L4:64 weakly excites
  12. L3:928 weakly excites
  13. L2:1841 weakly suppresses
  14. L6:2247 weakly excites
  15. L8:2006 weakly excites
  16. L4:46 weakly suppresses
  17. L6:2453 weakly suppresses
  18. L8:1623 weakly suppresses
  19. L2:2440 weakly suppresses
  20. L1:1517 weakly suppresses
  21. L6:1567 weakly excites colon introducing a summary point
  22. L2:2134 weakly suppresses
  23. L5:602 weakly excites
  24. L3:487 weakly suppresses

Feeds later layers

  1. L13:608 suppresses opening parenthesis starting an aside
  2. L12:1248 suppresses
  3. L16:2801 suppresses
  4. L17:1657 suppresses
  5. L12:878 suppresses
  6. L15:261 suppresses
  7. L12:1837 suppresses
  8. L17:1908 suppresses
  9. L11:1072 suppresses
  10. L17:2364 suppresses
  11. L12:1784 suppresses
  12. L10:1459 suppresses
  13. L10:1654 suppresses opening parenthesis before an acronym
  14. L10:271 excites
  15. L18:2081 suppresses
  16. L16:906 suppresses
  17. L14:1181 suppresses
  18. L10:1756 suppresses
  19. L16:2296 suppresses
  20. L14:1209 excites
  21. L14:1470 excites
  22. L16:2177 suppresses
  23. L17:1430 excites
  24. L15:2787 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 -5.97 and -5.801 values between -4.93 and -4.761 values between -4.76 and -4.581 values between -3.37 and -3.202 values between -2.85 and -2.681 values between -2.51 and -2.332 values between -2.33 and -2.161 values between -2.16 and -1.991 values between -1.99 and -1.813 values between -1.81 and -1.641 values between -1.64 and -1.475 values between -1.47 and -1.293 values between -1.12 and -0.957 values between -0.95 and -0.776 values between -0.77 and -0.6020 values between -0.60 and -0.4387 values between -0.43 and -0.25565 values between -0.25 and -0.081674 values between -0.08 and 0.091132 values between 0.09 and 0.27338 values between 0.27 and 0.4453 values between 0.44 and 0.612 values between 0.61 and 0.791 values between 0.79 and 0.96offnegativepositiveoften

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. THON
  2. ymes
  3. Simulator
  4. 发生
  5. amination
  6. uration
  7. 又好
  8. esus
  9. 排行
  10. imedia

Suppresses

  1. >i
  2. beit
  3. assuming
  4. ieri
  5. itionally
  6. 斯坦
  7. bé
  8. efficient
  9. śmy
  10. >j