Neuron Explorer

Qwen3-0.6B

'to' before an infinitive

A neuron in layer 24 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 the word 'to' when it comes before a verb, as in 'remains to be seen' or 'much work to be done'. Turning it up didn't produce a clear theme in the sample text.

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

    -ready anytime soon. But, as Rashid writes, it could be the start of something:⏎The results are still not perfect, and there is still much work to be done, but the technology is very promising, and we hope that in a

  2. #2 peak

    possible cause of paranoia.⏎A person suffering from paranoia will read a negative meaning from an innocent remark, will believe a certain person or people in general are “out to get him” and will stay preoccupied with unfounded doubts about the people around

  3. #3 peak

    Eaton||Maintainer|⏎Resources and communication⏎|Developer||VCS Repository Webview||http://www.octave.org/hg/octave|⏎|Required to build||GNU make|⏎|Required to build||a recent version of g++

  4. #4 peak

    into the abyss – all this has already been suggested by experts as an explanation.⏎Where does Sars-CoV-2 go in the brain?⏎It also remains to be clarified where the virus travels to the brain. John H. Morrison, professor

  5. #5 peak

    0 refugees to the shores of Cuba, Louisiana, Guatemala, Florida, and France between 1789 and 1809.2 Much remains to be known about the St. [End Page 37] Dominguan dias

  6. #6 peak

    - Where was Jesus born? (Matthew 2:1)⏎- Who was the king at that time? (Matthew 2:1)⏎- Who came to see Jesus? (Matthew 2:1)⏎- How did they know he

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: just was just re-introduce just was just, just was just, just was just... just was just... just was just... just was just... just was just... just was just... just was just... just was just... just was

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

    the border checkpoint at San Ysidro, California. “En nombre del cielo, les pido posada,” sings one group. “Pues no puede andar mi esposa am

  2. #2 peak

    otherwise he lives a normal life.⏎in normal circumstances, under normal circumstances en temps normal⏎→ In normal circumstances I would have resigned immediately.⏎to continue as normal se poursuivre normalement⏎→ Life in Israel will continue as normal.⏎w

  3. #3 peak

    to overcome a myriad of hurdles. plants use it to sprout branches no one gets covered and each gets maximum amount of sunlight, and as<|endoftext|>Помогите пожаааалуйста, сам не справляюсьY.

  4. #4 peak

    “Circassians are like a prism that shows just how polarized Israeli society is,” said Chen Bram, an anthropologist<|endoftext|>All classifieds – Veux-Veux-Pas, free classified ads Website.One moment, please⏎When

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. L21:853 strongly excites 'can' after 'and' or a noun subject
  2. L21:1521 strongly excites
  3. L20:2089 strongly suppresses
  4. L23:505 strongly suppresses
  5. L21:958 strongly excites
  6. L20:636 strongly suppresses
  7. L21:1657 suppresses
  8. L22:627 suppresses
  9. L23:257 suppresses
  10. L22:479 suppresses
  11. L18:1852 excites
  12. L20:2262 excites
  13. L19:545 excites
  14. L19:730 excites
  15. L23:373 suppresses 'to' after a noun or adjective
  16. L19:1769 excites
  17. L19:385 suppresses
  18. L20:2883 suppresses
  19. L23:30 suppresses
  20. L18:2303 suppresses
  21. L19:1678 excites
  22. L19:1208 suppresses
  23. L20:2527 excites
  24. L22:2258 suppresses

Feeds later layers

  1. L26:2432 strongly suppresses
  2. L27:2609 suppresses
  3. L27:964 suppresses
  4. L26:385 suppresses
  5. L27:412 suppresses
  6. L25:503 suppresses
  7. L25:1841 suppresses
  8. L27:427 weakly excites
  9. L27:565 weakly excites
  10. L25:529 weakly suppresses
  11. L27:461 weakly excites
  12. L25:810 weakly suppresses
  13. L25:347 weakly excites
  14. L25:566 weakly suppresses
  15. L26:1629 weakly suppresses
  16. L25:357 weakly suppresses
  17. L27:1059 weakly excites
  18. L25:108 weakly suppresses
  19. L27:1038 weakly suppresses
  20. L27:501 weakly suppresses
  21. L27:1899 weakly excites
  22. L27:2506 weakly excites
  23. L25:586 weakly excites
  24. L26:2741 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.

1 values between -12.72 and -12.031 values between -7.87 and -7.181 values between -5.79 and -5.103 values between -5.10 and -4.402 values between -3.71 and -3.024 values between -3.02 and -2.322 values between -2.32 and -1.6314 values between -1.63 and -0.94152 values between -0.94 and -0.253526 values between -0.25 and 0.45113 values between 0.45 and 1.1416 values between 1.14 and 1.8314 values between 1.83 and 2.536 values between 2.53 and 3.227 values between 3.22 and 3.916 values between 3.91 and 4.615 values between 4.61 and 5.304 values between 5.30 and 5.994 values between 5.99 and 6.686 values between 6.68 and 7.385 values between 7.38 and 8.072 values between 8.07 and 8.761 values between 8.76 and 9.462 values between 9.46 and 10.153 values between 12.23 and 12.924 values between 12.92 and 13.614 values between 14.31 and 15.00offnegativepositiveoften

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. ਯ
  2. 醒了
  3. 酩
  4. akening
  5. により
  6. ład
  7. rounded
  8. większ
  9. ayo
  10. Touches

Suppresses

  1. mieć
  2. łożyć
  3. fazer
  4. ивать
  5. hacer
  6. сделать
  7. использовать
  8. być
  9. contar
  10. ывать