Neuron Explorer

Qwen3-0.6B

'if' in conditional asides

A neuron in layer 11 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 'if' when it adds a condition at the end of a phrase, like 'Discard if the vaccine has been frozen' or 'printed out if required'. Turning it up gave text that was not clearly about conditions, so the steering results do not back up the 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

    application of color or tone.⏎14. Gen. Arrangement Drawing⏎Exterior view all components using line only and with sufficient detail to produce an Appearance Model if required. Usually drawn in third angle projection.⏎15. Detail Drawing⏎Contains

  2. #2 peak

    fields), not just specialists like Gonthier. His talk tomorrow, titled “Univalent Foundations,” will describe this, if he makes it in time<|endoftext|>New research leads to call for ban on hands-free

  3. #3 peak

    8°C (36° and 46°F). Do not freeze. Discard if the vaccine has been frozen.⏎A separate sterile syringe and needle must be used

  4. #4 peak

    , you can leave feedback. This video shows how to do this in Brightspace:⏎As you can see, a pdf serves double duty. Hand out hard copies if you wish… or upload them digitally so students can record their responses and submit them

  5. #5 peak

    of the whole of the original book. This CD has been bookmarked for easy⏎navigation, and pages can be searched, browsed, enlarged and printed out if required.<|endoftext|>IN-clusively MindedWe have signed our names to the

  6. #6 peak

    On what type of boundary was this?⏎Where was the most recent earthquake closest to you? Include the name of the city and state you reside in (or country if outside of the United States). Was it associated with a boundary?⏎Was there any

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 problem of the United States and the United Nations. The problem of the United Nations is a series of international negotiations that will involve a global effort in the design of a set of rules, which will be used to produce a set of global

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

    will walk in all the way which I command you, that it may be well with you.'⏎Matthew 7:24-27 “Therefore everyone who hears these words of Mine and acts on them, may

  2. #2 peak

    have any photos of this monument yet. Why don't you be the first to send us one?⏎If Google Street View is available, the image is from the best available vantage point looking, if possible,

  3. #3 peak

    nests, but the Son of Man has no place to rest."⏎American Standard Version⏎And Jesus said unto him, The foxes have holes, and the birds of the heaven have nests; but the Son of man hath not where to lay his

  4. #4 peak

    Holman Christian Standard BibleJesus told him, “Foxes have dens, and birds of the sky have nests, but the Son of Man has no place to lay His

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. L9:306 suppresses
  2. L6:2134 excites
  3. L4:265 suppresses
  4. L6:1881 excites
  5. L3:749 excites
  6. L9:2587 excites
  7. L4:1093 excites
  8. L0:1470 excites
  9. L10:358 weakly suppresses
  10. L9:1358 weakly excites
  11. L6:1925 weakly excites
  12. L0:1920 weakly excites
  13. L8:1866 weakly suppresses
  14. L8:691 weakly excites
  15. L9:3051 weakly suppresses
  16. L10:310 weakly excites
  17. L6:1203 weakly suppresses
  18. L5:1447 weakly suppresses
  19. L5:84 weakly suppresses
  20. L10:1241 weakly suppresses
  21. L4:2494 weakly suppresses
  22. L4:1834 weakly suppresses unclear: time spans and 'once you've'
  23. L8:2108 weakly excites
  24. L2:2765 weakly suppresses

Feeds later layers

  1. L15:513 excites
  2. L16:2167 excites
  3. L17:619 excites
  4. L16:2929 excites
  5. L15:2342 excites
  6. L16:2550 excites
  7. L17:1195 excites
  8. L19:2348 excites
  9. L13:696 excites
  10. L20:2066 excites
  11. L18:2311 excites
  12. L18:1606 excites
  13. L18:2235 excites
  14. L18:2778 excites
  15. L14:395 weakly excites
  16. L23:2705 weakly suppresses
  17. L18:2263 weakly excites
  18. L16:2323 weakly excites
  19. L16:2838 weakly excites
  20. L21:919 weakly excites
  21. L18:2783 weakly excites
  22. L16:1342 weakly excites
  23. L17:2729 weakly excites
  24. L19:2573 weakly excites "of" after a percentage or share

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 -1.44 and -1.241 values between -1.04 and -0.8413 values between -0.64 and -0.44276 values between -0.44 and -0.231651 values between -0.23 and -0.031730 values between -0.03 and 0.17195 values between 0.17 and 0.3714 values between 0.37 and 0.578 values between 0.57 and 0.773 values between 0.77 and 0.972 values between 0.97 and 1.171 values between 1.17 and 1.372 values between 1.37 and 1.572 values between 1.57 and 1.771 values between 1.77 and 1.973 values between 2.17 and 2.381 values between 2.38 and 2.581 values between 2.98 and 3.182 values between 3.58 and 3.781 values between 6.39 and 6.59offnegativepositiveoften

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. emode
  2. 给您
  3. Globals
  4. そうで
  5. 您
  6. oxid
  7. 不利
  8. stein
  9. 你不
  10. _URI

Suppresses

  1. rics
  2. theirs
  3. razón
  4. atas
  5. görünt
  6. 大地
  7. ly
  8. 麼
  9. tempt
  10. LY