Neuron Explorer

Qwen3-0.6B

'of' after a title or event noun

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

The neuron fires on small connecting words like 'of' or 'into' that come after a noun or verb and before a name, date or place, such as 'Captain of the Guard' or 'in October of 1904'. It is mixed, and the steering samples don't clearly match.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

    that changes how the⏎cd command works. Normally when you try and cd⏎into a directory, it will only try and change to the path specified from the current

  2. #2 peak

    ennials and subshrubs) and 2008 (volume 2- ground covers and edgers). Sadly, Carolyn Singer passed away in July of 2019, but her writing still provides vast insight into foothill

  3. #3 peak

    basic necessities of daily living.⏎Pennsylvania state law required that mining companies and company stores be incorporated separately. Therefore, the Heilwood Company was incorporated in October of 1904 for “the purpose of carrying on a general mercant

  4. #4 peak

    who have coronary artery disease, especially those who have suffered myocardial infarctions ("heart attacks") in the past⏎- Individuals who have congestive heart failure of any cause⏎- Individuals with intrinsic heart muscle disease such as hypertrophic cardiomy

  5. #5 peak

    no keys can map, or hash to. So this can be quite a topic.⏎How does hashing relate to hash joins? In hash joins, we will be joining two tables. We read the first table and apply a hash function to each record

  6. #6 peak

    , as well, such as by coughing into a contracted elbow.⏎Moreover, stay aware of the most recent information on the outbreak

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 calculus of one variable (to use) in the form of a function of a day. When I come to know it, I can use it to be in the country, and the other side of the day. So, if 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

    twig among millions on the<|endoftext|>Commemorations for Kiahk 15⏎This day marks the departure of St. Gregory, the Patriarch of the Armenians who was a martyr, without bloodshed (A Confessor). This

  2. #2 peak

    swung open and the Captain of the Guard strode into the room with a royal warrant for Cromwell’s arrest on

  3. #3 peak

    1837. A hero of the Civil War and Spanish-American War, he was the first, and to date only, person promoted to Admiral of the Navy.⏎Marihuana Tax Act of 1937⏎On August

  4. #4 peak

    the next solar maximum, due in 2013, the chance of big magnetic storms is on the increase. On average you might expect to see aurora in the far north of Scotland every few months, but less often as you travel

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. L6:272 weakly suppresses
  2. L6:1799 weakly excites
  3. L5:860 weakly excites
  4. L4:2022 weakly suppresses
  5. L2:2420 weakly excites
  6. L1:1768 weakly excites
  7. L4:2055 weakly suppresses
  8. L0:2352 weakly excites
  9. L6:1200 weakly suppresses
  10. L6:1350 weakly suppresses
  11. L5:856 weakly suppresses
  12. L5:2200 weakly suppresses
  13. L4:1528 weakly excites
  14. L3:1314 weakly suppresses
  15. L1:1583 weakly excites
  16. L3:728 weakly suppresses
  17. L5:1560 weakly excites
  18. L6:2059 weakly suppresses
  19. L5:2636 weakly suppresses
  20. L6:1288 weakly excites
  21. L4:2560 weakly excites
  22. L1:2109 weakly excites
  23. L5:2528 weakly excites
  24. L2:1977 weakly excites

Feeds later layers

  1. L19:1442 weakly suppresses
  2. L11:825 weakly excites
  3. L9:116 weakly suppresses
  4. L16:1272 weakly excites
  5. L9:209 weakly suppresses
  6. L20:2770 weakly suppresses
  7. L21:1315 weakly excites
  8. L19:2486 weakly suppresses
  9. L10:1034 weakly excites
  10. L18:1428 weakly excites
  11. L13:743 weakly excites
  12. L10:930 weakly excites
  13. L17:801 weakly suppresses
  14. L9:296 weakly excites
  15. L9:646 weakly excites
  16. L8:364 weakly suppresses
  17. L22:157 weakly excites
  18. L10:2035 weakly excites
  19. L15:620 weakly excites
  20. L16:1984 weakly excites
  21. L13:2260 weakly excites
  22. L25:2403 weakly suppresses
  23. L20:285 weakly suppresses
  24. L24:1816 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 -2.68 and -2.561 values between -1.49 and -1.372 values between -1.37 and -1.255 values between -1.25 and -1.131 values between -1.13 and -1.014 values between -1.01 and -0.899 values between -0.89 and -0.773 values between -0.77 and -0.659 values between -0.65 and -0.5322 values between -0.53 and -0.4185 values between -0.41 and -0.29305 values between -0.29 and -0.17806 values between -0.17 and -0.051694 values between -0.05 and 0.07687 values between 0.07 and 0.18191 values between 0.18 and 0.3052 values between 0.30 and 0.4215 values between 0.42 and 0.546 values between 0.54 and 0.663 values between 0.66 and 0.783 values between 0.78 and 0.901 values between 1.38 and 1.501 values between 1.50 and 1.621 values between 1.86 and 1.971 values between 1.97 and 2.09offnegativepositiveoften

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. cross
  2. null
  3. final
  4. key
  5. :e
  6. estone
  7. prime
  8. dup
  9. ing
  10. NaN

Suppresses

  1. achable
  2. ось
  3. houses
  4. счита
  5. 药师
  6. 级以上
  7. ��
  8. classified
  9. angers
  10. hausen