Neuron Explorer

Qwen3-0.6B

'to' after come or bring

A neuron in layer 7 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' in phrases like 'came to be', 'come to see', and 'brought it to my attention', where a verb of arriving or bringing is followed by 'to'. Its negative side is 'to' in 'change to' or 'by' in 'replaced by', which are different uses. Turning it up gave text with no clear link to these phrases.

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

    book, The Price of Privilege, Marilyn Levine tries to make sense of this trend: “When parents place an excessively high value on outstanding performance, children come to see anything less than perfection as failure. While most kids hang in there and try

  2. #2 peak

    that their soldiers were well-supplied with ample shields.⏎Shields were used by both the cavalrymen and infantrymen in a Carolingian army. This came to be due to the fact that Carolingian shields were very inexpensive and even common

  3. #3 peak

    complexity of individuals relationships to the world they live in and the effects on individual health of pollution, poverty, and unhealthy social norms and values are ignored. People come to construe healthy behavior in terms of dependency on a medical industry that constantly invents

  4. #4 peak

    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 inside

  5. #5 peak

    Quality Control (QC) and Testing. Though they’re closely related, they are, ultimately, different.⏎If you work in the IT industry, you’ve probably come across them. You’ve also probably noticed that many executives – and customers – don

  6. #6 peak

    Believe it or not, the sauce was brought to France by an Italian chef called Catherina de Medici in the 1

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: a more detailed and comprehensive plan of a 10-day plan for a 10-week plan. So I will just focus on the 10-day plan. So I will just focus on the 10-day plan for a

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

    : ‘do not’ would change to ‘don’t’⏎That’s it, you’ve got it…. Now write

  2. #2 peak

    follow this rule (as in soliloquies).⏎Add -s to most nouns ending in -f.⏎Exceptions: In some cases, change the -f to -v and add -es⏎In compound words, make the main word plural

  3. #3 peak

    .⏎- If stuck for choice, pick the best of a bad bunch;⏎Long commutes to, from or during work can mean that sit-down meals are replaced by unhealthy foods on the go. It also means that you are constantly exposed to food

  4. #4 peak

    remove the carriage return and replace it with a space, and then break your line of text at a point that is convenient

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. L6:984 suppresses
  2. L2:750 excites
  3. L6:1702 suppresses "not" or "instead" contrasting a correction
  4. L3:1152 suppresses
  5. L5:1671 weakly excites
  6. L4:1531 weakly suppresses
  7. L4:2177 weakly excites
  8. L4:328 weakly suppresses 'to' after 'so as' and infinitive cues
  9. L1:2630 weakly suppresses
  10. L5:548 weakly excites
  11. L1:2525 weakly excites
  12. L5:3009 weakly excites 'to' after a verb or noun
  13. L1:906 weakly suppresses
  14. L4:2961 weakly excites
  15. L5:2867 weakly excites
  16. L4:2111 weakly excites
  17. L6:1974 weakly excites
  18. L4:123 weakly suppresses
  19. L4:1847 weakly suppresses
  20. L5:770 weakly suppresses
  21. L6:2451 weakly suppresses
  22. L5:1802 weakly suppresses
  23. L4:1236 weakly excites
  24. L5:2057 weakly suppresses

Feeds later layers

  1. L9:723 suppresses
  2. L16:937 suppresses
  3. L11:1895 suppresses
  4. L17:429 suppresses
  5. L17:2007 suppresses
  6. L13:383 excites
  7. L14:785 suppresses
  8. L23:477 weakly suppresses
  9. L20:1465 weakly suppresses
  10. L9:2301 weakly excites
  11. L16:2763 weakly excites
  12. L15:2958 weakly suppresses
  13. L15:1238 weakly excites 'less' before a comparative or negative effect
  14. L16:804 weakly excites
  15. L8:909 weakly excites
  16. L15:428 weakly suppresses
  17. L15:2981 weakly suppresses
  18. L13:2082 weakly suppresses
  19. L18:2919 weakly suppresses
  20. L9:3000 weakly excites
  21. L8:2298 weakly suppresses
  22. L25:2288 weakly excites
  23. L17:2598 weakly suppresses
  24. L12:2168 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 -3.07 and -2.961 values between -1.98 and -1.871 values between -1.87 and -1.762 values between -1.76 and -1.651 values between -1.65 and -1.541 values between -1.54 and -1.431 values between -1.43 and -1.322 values between -1.32 and -1.211 values between -1.21 and -1.101 values between -1.10 and -0.991 values between -0.99 and -0.884 values between -0.88 and -0.773 values between -0.77 and -0.666 values between -0.66 and -0.5513 values between -0.55 and -0.4426 values between -0.44 and -0.3381 values between -0.33 and -0.22343 values between -0.22 and -0.111286 values between -0.11 and -0.001397 values between -0.00 and 0.11499 values between 0.11 and 0.22170 values between 0.22 and 0.3341 values between 0.33 and 0.4411 values between 0.44 and 0.556 values between 0.55 and 0.664 values between 0.66 and 0.772 values between 0.77 and 0.881 values between 1.10 and 1.212 values between 1.21 and 1.32offnegativepositiveoften

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. !.⏎⏎
  2. 头发
  3. evaluation
  4. getData
  5. ucket
  6. 大发
  7. braco
  8. 的灵魂
  9. 似的
  10. kitchens

Suppresses

  1. 另一
  2. 新一代
  3. =current
  4. دد
  5. 明年
  6. 二线
  7. ymi
  8. conserve
  9. ampa
  10. yms