Neuron Explorer

Qwen3-0.6B

'the' before a noun after 'of'

A neuron in layer 10 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 'the' when it comes right after a preposition like 'of' or 'to', just before a noun, as in 'the back of the book' or 'the stem of the plant'. Its negative side is weak and not clearly related. Turning it up gave text that did not clearly show this 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

    for goods or services in some instances.⏎What are the different types of crypto on the market?⏎To put it simply, there are literally thousands of different cryptocurrencies on the

  2. #2 peak

    adults focus on the value of being in the class and helping the class become a successful place of learning.⏎The instructor presented a survey to the students on the first day about the merit of participation; and, how participation can

  3. #3 peak

    behind enemy lines for much longer than this and by 15 November all members of 1st Para Bn's detachment and most of 2nd Para Bn's detachment were unaccounted for.⏎The mission was extremely hazardous for the

  4. #4 peak

    of symmetry as well).⏎: A parabola is the set of all points in a plane that are equidistant from the focus and the directrix of the parabola. [Adopted from iCoachMath]⏎Focus:Focus

  5. #5 peak

    organized to allow easier administration of the tests in the classroom. Each test has a total score of 100.⏎An optional listening exercise at the back of the book for each unit, using the recordings from the Student’s Book.⏎An Answer

  6. #6 peak

    by the plague bacillus, ingests bacilli which may multiply to such an extent that they completely block a valve-like organ at the entrance to the stomach of the flea. When such a flea deserts the host rat and transfers to a human

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: as a point in the past, and in the context of the past, it's important to think of it as a tool that the people of the day, and in the sense, that it's important to be remembered as a historical figure

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

    outnumber the colonists. New England, New York, Virginia, and South Carolina were scenes of numerous wars in the 17th century. In 1622, Indians killed a third of the one thousand settlers in Virginia. Another

  2. #2 peak

    a (in male striped seals) or from the esophagus (in male walruses) and serve to alter the specific gravity of the body; and (4) in the sperm whale, a blind air sac about 1 cu m

  3. #3 peak

    realish, 15. James Grealish (Michl), 16. John Carr (Pat), 17. Michael Sheridan, 18. Peter Grealish

  4. #4 peak

    1989, it was among the first 25 featured films to be preserved in the Library of Congress’ National Film Registry, and in 2008, the American Film Institute named it the greatest animated film of all time

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. L8:149 suppresses
  2. L9:152 suppresses
  3. L9:259 suppresses
  4. L9:749 excites
  5. L6:93 suppresses
  6. L8:9 excites
  7. L6:136 excites
  8. L7:26 suppresses
  9. L7:112 suppresses
  10. L9:682 excites
  11. L9:103 suppresses "as" or "since" giving a reason
  12. L8:182 excites
  13. L8:8 suppresses
  14. L4:274 excites
  15. L7:1197 suppresses
  16. L9:145 suppresses
  17. L6:205 suppresses
  18. L8:197 suppresses
  19. L8:506 suppresses
  20. L7:35 suppresses
  21. L8:71 excites
  22. L6:1006 excites
  23. L8:179 excites
  24. L9:270 suppresses

Feeds later layers

  1. L11:222 suppresses
  2. L17:334 excites
  3. L17:29 weakly excites
  4. L11:234 weakly excites
  5. L16:2279 weakly excites
  6. L18:660 weakly excites
  7. L20:1169 weakly suppresses
  8. L27:258 weakly excites
  9. L11:796 weakly suppresses
  10. L15:764 weakly excites
  11. L11:56 weakly excites
  12. L12:77 weakly excites
  13. L12:1844 weakly suppresses
  14. L17:43 weakly excites
  15. L20:1621 weakly suppresses
  16. L15:487 weakly excites
  17. L16:1630 weakly excites
  18. L17:459 weakly excites
  19. L13:23 weakly excites
  20. L12:808 weakly excites
  21. L20:17 weakly excites
  22. L27:309 weakly excites
  23. L11:1776 weakly excites
  24. L19:398 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.

3 values between -2.51 and -2.312 values between -2.31 and -2.114 values between -2.11 and -1.914 values between -1.91 and -1.7111 values between -1.71 and -1.5118 values between -1.51 and -1.3138 values between -1.31 and -1.1142 values between -1.11 and -0.9178 values between -0.91 and -0.71147 values between -0.71 and -0.51231 values between -0.51 and -0.31520 values between -0.31 and -0.111609 values between -0.11 and 0.09570 values between 0.09 and 0.29267 values between 0.29 and 0.49205 values between 0.49 and 0.6988 values between 0.69 and 0.8922 values between 0.89 and 1.0910 values between 1.09 and 1.297 values between 1.29 and 1.4913 values between 1.49 and 1.696 values between 1.69 and 1.892 values between 1.89 and 2.094 values between 2.09 and 2.291 values between 2.29 and 2.492 values between 2.49 and 2.691 values between 2.69 and 2.891 values between 2.89 and 3.091 values between 3.69 and 3.891 values between 5.29 and 5.48offnegativepositiveoften

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. ario
  2. eres
  3. 游艇
  4. wood
  5. riba
  6. wend
  7. 下面是
  8. rowning
  9. edian
  10. este

Suppresses

  1. too
  2. syst
  3. .'.$
  4. ’)
  5. ’:
  6. .Seek
  7. shrimp
  8. Hun
  9. .')
  10. gu