Neuron Explorer

Qwen3-0.6B

'of' after end, top or bottom

A neuron in layer 5 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 lights up on the word 'of' in place or time phrases like 'end of', 'beginning of', 'top of' and 'bottom of the page'. It is one of the strongest neurons in this set, but turning it up or down did not show a clear theme in the written 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

    currently based out of USCG’s Research and Development Centre in New London Connecticut, approximately 375 nautical miles from where the Titanic sank. From beginning of February to the end of July (ice season), the IIP patrols the oceans

  2. #2 peak

    but there was hardly ever anything to be seen due to bad weather or nighttime ;). The site states that the cam needs to be rehoused as of end of December 2013 which has not happened yet.⏎If the cam comes

  3. #3 peak

    America's working men and women by setting and enforcing standards, and providing training, education and assistance. For more information, visit www.osha.gov.<|endoftext|>End of the year math review for 2nd grade can be FUN! 2nd

  4. #4 peak

    at the top of your screen near the toolbars. Then right-click and select AutoCAD. A

  5. #5 peak

    signed up to receive the notifications of new studies, you can do that today (the form is at the bottom of the page).⏎Esther – Day 3⏎Xerxes wanted to show

  6. #6 peak

    emissions, driven by driving efficiency measures and lightweighting, is therefore going to increase the absolute share of emissions generated in the production of the car and in its end-of-life phases.⏎Full LCA analyses on all car models⏎Within the next five

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: ... and the 200-word limit. This is a personal and professional story about the current. The topic is about... the user is...... and the user is... I have to you by... the topic... and so much

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

    system, attacking other nerve cells, and spreading to other areas of the brain.⏎In diabetic monkeys, the virus was also found in the so-called entorhinal cortex, which also plays an important role in Alzheimer’s disease. If the

  2. #2 peak

    metal into a die (or mold) to create a specific shape. Once the metal cools, the casting is removed from the mold, and you have your finished shape (more or less).⏎A good example of casting in modern manufacturing is the

  3. #3 peak

    ; ending in a point: as, a peaked beard.⏎- Having a sickly, thin

  4. #4 peak

    ,” Cook added. “Government scientists have found disturbing concentrations of pesticides in some baby foods. And the U.S. Department of Agriculture has found weed killers widespread in finished tap water. Environmentalists have had important successes in forcing pesticides that presented unaccept

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. L4:742 suppresses
  2. L4:1721 excites the gap before a decade or century
  3. L4:925 suppresses
  4. L4:1712 weakly suppresses
  5. L4:2114 weakly excites
  6. L4:2866 weakly excites the word 'average' before a quantity
  7. L3:1394 weakly suppresses
  8. L4:1728 weakly suppresses
  9. L1:1428 weakly suppresses
  10. L2:2208 weakly excites
  11. L4:385 weakly excites multiplication and scaling in math
  12. L4:2374 weakly suppresses mixed: finance terms, strongly negative on systolic
  13. L0:415 weakly excites
  14. L3:1252 weakly excites
  15. L2:2052 weakly suppresses
  16. L2:2328 weakly suppresses
  17. L3:2350 weakly excites
  18. L4:2025 weakly suppresses
  19. L2:2593 weakly excites
  20. L3:1352 weakly suppresses
  21. L0:1338 weakly suppresses
  22. L4:1902 weakly excites
  23. L1:1025 weakly suppresses
  24. L4:2086 weakly suppresses

Feeds later layers

  1. L16:1542 excites
  2. L10:2192 excites
  3. L15:871 excites
  4. L17:1445 excites
  5. L9:2391 excites
  6. L17:2677 weakly excites
  7. L18:2148 weakly excites
  8. L21:1408 weakly excites
  9. L12:1251 weakly excites
  10. L13:919 weakly excites
  11. L11:2202 weakly excites
  12. L12:637 weakly excites
  13. L7:1941 weakly excites
  14. L11:350 weakly suppresses
  15. L17:2052 weakly suppresses
  16. L6:766 weakly suppresses
  17. L23:2043 weakly excites
  18. L17:1138 weakly suppresses
  19. L10:1765 weakly excites
  20. L11:1365 weakly suppresses
  21. L9:3061 weakly excites
  22. L11:560 weakly excites
  23. L8:564 weakly suppresses
  24. L20:1192 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.

5 values between -0.80 and -0.5643 values between -0.56 and -0.32718 values between -0.32 and -0.092788 values between -0.09 and 0.15305 values between 0.15 and 0.3916 values between 0.39 and 0.636 values between 0.63 and 0.877 values between 0.87 and 1.115 values between 1.11 and 1.352 values between 1.35 and 1.591 values between 1.59 and 1.832 values between 2.06 and 2.303 values between 2.30 and 2.541 values between 2.54 and 2.781 values between 3.26 and 3.502 values between 3.74 and 3.971 values between 4.69 and 4.931 values between 6.12 and 6.361 values between 8.51 and 8.75offnegativepositiveoften

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. acement
  2. stice
  3. ñe
  4. /end
  5. utoff
  6. aque
  7. REATE
  8. 浒
  9. Aligned
  10. ing

Suppresses

  1. _component
  2. degrees
  3. 成分
  4. 恺
  5. .persist
  6. Meteor
  7. ********************************************************************************
  8. 生于
  9. _components
  10. ippers