Neuron Explorer

Qwen3-0.6B

"to" after come or brought

A neuron in layer 21 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" after verbs like "come", "brought" or "bring", as in "come to an end" or "brought to market". Turned up, the model produced loops around "to the moon" and "towards". Turned down, it went into "us" and name fragments 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

    resulted in punishment. Using “narrative” or “story” history to describe the interview sidesteps an unintended reference to oralism that may be brought to mind with the word “oral” and can help build rapport with the interviewee

  2. #2 peak

    can even make it to industrial-scale production. Neither of these approaches addresses, seriously, the potential that the technologies suggest. Potential that deserves to be explored and brought to market.⏎Before addressing the potential impact of the research and the responses to it,

  3. #3 peak

    at this point, the up or down state could not be accurately predicted, thus, it wouldnt be useful for much of anything. To make the switch come to rest in a predetermined up or down state, the researchers applied a laser with a

  4. #4 peak

    ne periodically boosted the space station's orbit, and in fact helped the station dodge a passing piece of Russian space junk last month.⏎But all good things must come to an end: Unlike the Italian-built space cargo modules that are carried back and forth

  5. #5 peak

    to your provider until you are stable.⏎Treatment usually includes:⏎- Sedative drugs to help ease withdrawal symptoms⏎<|endoftext|>THE extermination of European Jewry has come to epitomise absolute evil in our version of the history of the 20

  6. #6 peak

    support your teaching of the religious festivals that occur in the spring time.<|endoftext|>welcome to the second course in the reinforcement learning specialization: sample-based learning methods, brought to you by the university of alberta, onlea, and coursera

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: to the back to back to back to... to the back to back to... on into the home. This is into the home, to the back to the back to... home. This is back to the back to... home. This

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

    all of our questions through research.⏎The school bus came at 9:30 on a cold, windy, soggy day and picked us up to take us to Fort Whyte. We arrived at about 10:00.

  2. #2 peak

    her family to go with Wentworth to Lyme.⏎- Louisa jumps off the Cobb steps and knocks herself unconscious on the ground.⏎- Captain Wentworth carries Louisa to the Harvilles’ home.⏎- The doctor says that Louisa will

  3. #3 peak

    ibullah sought sanctuary in the UN compound in Kabul. He remained there until September 1996 when the Taliban captured Kabul. The Taliban dragged Najibullah from the UN compound and hanged him from a traffic light post in the streets

  4. #4 peak

    conquering hero, greeted with palm branches and loud hosannas. But Holy Week reaches its climax on Good Friday, when Jesus is crowned with thorns and led out of the city like a common criminal, on to crucifixion, death

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. L20:2310 suppresses
  2. L16:959 suppresses
  3. L17:2740 excites
  4. L19:1951 suppresses
  5. L20:650 excites
  6. L18:1069 suppresses
  7. L13:1724 suppresses
  8. L10:1401 weakly excites
  9. L17:2938 weakly suppresses
  10. L19:966 weakly excites
  11. L18:1718 weakly suppresses
  12. L10:3057 weakly suppresses
  13. L6:2686 weakly excites
  14. L16:2602 weakly suppresses
  15. L18:1352 weakly suppresses
  16. L19:1871 weakly suppresses
  17. L8:2018 weakly excites
  18. L10:1689 weakly suppresses
  19. L10:1374 weakly suppresses
  20. L12:952 weakly suppresses
  21. L5:2155 weakly excites
  22. L8:1977 weakly suppresses
  23. L0:2916 weakly excites
  24. L9:1351 weakly suppresses

Feeds later layers

  1. L24:2343 strongly suppresses
  2. L22:2937 strongly suppresses
  3. L23:2053 suppresses
  4. L24:1333 suppresses
  5. L22:2389 suppresses
  6. L23:1182 suppresses
  7. L27:1564 suppresses
  8. L22:2622 suppresses
  9. L25:1990 suppresses
  10. L25:2159 suppresses
  11. L27:2816 suppresses
  12. L22:2591 suppresses
  13. L23:1660 suppresses
  14. L24:1070 suppresses
  15. L27:1686 suppresses
  16. L22:818 suppresses
  17. L25:2505 suppresses
  18. L26:1355 weakly suppresses
  19. L22:2734 weakly suppresses
  20. L25:2265 weakly suppresses the word 'directly' mid-sentence
  21. L23:570 weakly suppresses
  22. L23:102 weakly excites
  23. L22:2670 weakly suppresses
  24. L23:1803 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 -44.88 and -43.491 values between -29.68 and -28.301 values between -25.54 and -24.151 values between -22.77 and -21.392 values between -21.39 and -20.012 values between -20.01 and -18.632 values between -18.63 and -17.252 values between -17.25 and -15.874 values between -15.87 and -14.481 values between -14.48 and -13.102 values between -13.10 and -11.723 values between -11.72 and -10.342 values between -10.34 and -8.962 values between -8.96 and -7.585 values between -7.58 and -6.2011 values between -6.20 and -4.8115 values between -4.81 and -3.4328 values between -3.43 and -2.0598 values between -2.05 and -0.673192 values between -0.67 and 0.71514 values between 0.71 and 2.099 values between 2.09 and 3.483 values between 3.48 and 4.861 values between 4.86 and 6.243 values between 6.24 and 7.621 values between 7.62 and 9.002 values between 9.00 and 10.38offnegativepositiveoften

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. resse
  2. cript
  3. تين
  4. oten
  5. 差别
  6. -scrollbar
  7. NewLabel
  8. atención
  9. özel
  10. fer

Suppresses

  1. into
  2. towards
  3. toward
  4. Into
  5. hacia
  6. upwards
  7. INTO
  8. into
  9. backwards
  10. 往