Neuron Explorer

Qwen3-0.6B

'to' after 'put' (put to use)

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 most on the word 'to' in phrases like 'put to use', 'put to death', and 'put to a writer', and on similar verb plus 'to' pairs. It turns off on technical economics words like 'equilibrium', 'solutions', and 'variables'. Turning it up did not bring out a clear theme in the generated 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

    reconciled will be crucial.⏎Meanwhile, the Sanders-Boxer Global Warming Pollution Reduction Act, currently in committee in the Senate, would put smart-energy solutions to work right now to solve global warming and also create new economic opportunities and hundreds of

  2. #2 peak

    and with a few modifications the arc was struck.⏎It’s not a finished project yet, and we’re looking forward to seeing how [GreatScott!] puts this to use. For now, we’re grateful for the lesson is Royer oscillators

  3. #3 peak

    istic reforms and translated the Bible into his native tongue.⏎Many Poles turned from the Roman Church, winning a measure of religious freedom. Some church buildings were put to Protestant use. Laws forbade the execution of Roman Church decrees

  4. #4 peak

    59; died at Madrid, 27 March, 1625. He was a great-grandson of the Tordesillas who was put to death by the Comuneros at Seville. He studied in Spain and Italy

  5. #5 peak

    b) Write down the consumers budget constraint and characterize the solution to her intertemporal maximization problem.⏎c) Consider the full competitive market equilibrium in this economy; normalize

  6. #6 peak

    credibility. It would not be an exaggeration to say that from ancient times until now, there has not been a period in which this question has not been put to a writer or an artist without regard to his nationality or the motives for his departure

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 find the number of ways. In this case, the problem is to find the number of ways the students can choose their preferences, which is the number of ways to choose the students, and to find the number of ways to choose 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

    match experimental results found in the literature. These results are for steady-state solutions; a dynamic implementation requires transient modeling as well. This can be achieved by extending

  2. #2 peak

    of supply and demand. Any shift in one of these results in a price change that signals a corresponding shift in the other. Then, the prices return to an equilibrium level. A market failure results when prices cannot achieve equilibrium because of market distortions

  3. #3 peak

    models are applied to problems with the following characteristics:⏎The problem has a well-defined sole objective.⏎There are alternative courses of action to resolve the problem.⏎The decision variables are continuous and they can accept any fractional or non-negative values within the particular range

  4. #4 peak

    in Congressional Primaries, 1994-2004⏎|Pluralities Avoided by Runoffs||77|⏎|Candidates Elected After Plurality Primary Victory|⏎|Candidates Elected After Runoff Victory|⏎

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. L6:1236 excites
  2. L6:2209 excites
  3. L3:1299 suppresses
  4. L3:705 weakly suppresses
  5. L5:1297 weakly excites
  6. L6:400 weakly suppresses
  7. L4:954 weakly suppresses
  8. L6:1862 weakly excites
  9. L3:2922 weakly excites
  10. L5:2096 weakly excites
  11. L4:1186 weakly excites
  12. L6:2435 weakly excites
  13. L6:742 weakly suppresses
  14. L5:91 weakly excites
  15. L6:7 weakly suppresses
  16. L4:1379 weakly suppresses
  17. L4:2040 weakly suppresses
  18. L5:1334 weakly suppresses
  19. L6:1147 weakly excites
  20. L3:105 weakly excites
  21. L4:879 weakly excites
  22. L0:2081 weakly excites
  23. L0:2529 weakly excites
  24. L2:2607 weakly excites

Feeds later layers

  1. L10:1311 excites
  2. L8:141 excites
  3. L12:1989 suppresses
  4. L8:246 suppresses
  5. L12:650 weakly excites
  6. L12:1908 weakly excites
  7. L12:793 weakly suppresses
  8. L8:767 weakly suppresses
  9. L11:1634 weakly excites
  10. L15:2531 weakly excites
  11. L14:583 weakly excites
  12. L21:3055 weakly excites
  13. L25:489 weakly suppresses
  14. L9:637 weakly excites
  15. L11:1959 weakly excites
  16. L22:1336 weakly excites
  17. L18:658 weakly suppresses
  18. L9:1844 weakly excites
  19. L11:86 weakly excites
  20. L12:2764 weakly suppresses
  21. L9:1290 weakly suppresses
  22. L10:1513 weakly suppresses
  23. L23:1909 weakly suppresses
  24. L9:2233 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.

2 values between -1.59 and -1.521 values between -1.19 and -1.131 values between -0.93 and -0.861 values between -0.86 and -0.801 values between -0.73 and -0.662 values between -0.66 and -0.605 values between -0.53 and -0.4711 values between -0.47 and -0.4026 values between -0.40 and -0.3365 values between -0.33 and -0.27126 values between -0.27 and -0.20255 values between -0.20 and -0.14455 values between -0.14 and -0.07857 values between -0.07 and -0.00946 values between -0.00 and 0.06552 values between 0.06 and 0.13329 values between 0.13 and 0.19168 values between 0.19 and 0.2667 values between 0.26 and 0.3319 values between 0.33 and 0.3911 values between 0.39 and 0.464 values between 0.46 and 0.521 values between 0.52 and 0.592 values between 0.85 and 0.921 values between 0.99 and 1.05offnegativepositiveoften

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. posable
  2. ailing
  3. ibe
  4. arching
  5. ometric
  6. iping
  7. abei
  8. reamble
  9. <UFunction
  10. определен

Suppresses

  1. solutions
  2. Nazis
  3. mium
  4. 结论
  5. solution
  6. Auschwitz
  7. 结果
  8. :NS
  9. azz
  10. mage