Neuron Explorer

Qwen3-0.6B

'those' standing in for a noun in comparisons

A neuron in layer 14 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 "those" (or "one") when it stands in for a noun in a comparison, as in "better than those of other countries." When it was turned up, the model's writing drifted into rambling, unrelated text, so the effect on its output was not clearly readable.

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

    More Info... by email⏎Consumer ethnocentrism is a psychological concept that refers to individuals who believe that their country's products are superior to those of other countries. This concept also describes consumers in one country thinking that purchasing products

  2. #2 peak

    are more "right-beaked" crossbills than left-beaked? Birds that have the lower mandible crossing to the right are three times more common than those with a left-crossing lower mandible.⏎- White-winged Crossbills

  3. #3 peak

    magnetic pole. They find that over a short period, possibly only a few centuries, the pole leapt from a location oriented around 45 degrees south to one near 45 degrees north. The paleomagnetic pole then drifted through around

  4. #4 peak

    , right? See it in action below, and check out the project’s elaborate overview here.<|endoftext|>Our system of government is different from those of all other nations, because part of the political power is vested in the State

  5. #5 peak

    an odd shape in the mutant mice: Their axons and dendrites are shorter and have fewer branches than those of controls. The shortage of branches may translate to fewer synapses, or neuronal

  6. #6 peak

    conscientiousness and signs of the disease. The brains of the conscientious had similar levels of plaques and tangles which build up and cause Alzheimer's as those of the less conscientious.⏎Dr Wilson said this was not unexpected. He said

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 current and the current's current, and the current's current's current's current's current's current's current's current's current's current's current's current's current's current's current's current's current's current's current's

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

    , began to terrorize Iraqi cities and towns. Al-Qaida in Iraq recruited from other countries to build its influence and keep a democratic nation from arising in the region.⏎As the challenges of helping to form a free Iraq began to

  2. #2 peak

    soldiers and enemies, is fraught with danger. Along the treacherous path to Belgium the three children skate using every bit of speed, courage, and strength they can muster. All the time they

  3. #3 peak

    be one of the largest in the area. For surrounding landowners, the project will promote different methods of long-term forest

  4. #4 peak

    around 400 CE. The oldest inscription is written in faulty Sanskrit. After this, inscriptions alternate between Sanskrit and the Cham language of the times.⏎Cham kings studied classical Indian texts such as the Dharmaśāstra

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. L13:2436 excites
  2. L6:345 weakly excites
  3. L7:1179 weakly suppresses
  4. L12:575 weakly suppresses
  5. L8:1001 weakly suppresses
  6. L13:2983 weakly suppresses
  7. L13:1173 weakly excites
  8. L8:1990 weakly suppresses
  9. L6:2276 weakly excites
  10. L13:533 weakly suppresses
  11. L10:1329 weakly suppresses
  12. L12:1290 weakly excites mid-word fragments in names
  13. L12:1047 weakly suppresses
  14. L10:583 weakly excites
  15. L6:2417 weakly suppresses
  16. L1:1794 weakly excites
  17. L1:2119 weakly excites
  18. L2:1781 weakly suppresses
  19. L4:390 weakly excites "and" joining abstract nouns
  20. L13:2796 weakly excites
  21. L13:44 weakly excites inside web addresses and citations
  22. L1:2539 weakly excites
  23. L6:924 weakly excites
  24. L11:546 weakly suppresses

Feeds later layers

  1. L15:851 excites
  2. L16:662 suppresses
  3. L15:1902 excites
  4. L17:177 excites
  5. L18:68 excites
  6. L15:795 excites
  7. L17:76 excites
  8. L17:1918 excites
  9. L20:284 excites
  10. L16:2715 excites
  11. L17:1167 excites
  12. L18:1143 excites
  13. L18:579 excites
  14. L15:733 suppresses
  15. L19:211 excites
  16. L17:181 excites
  17. L21:665 excites
  18. L20:55 suppresses
  19. L17:2037 excites
  20. L15:1601 suppresses
  21. L15:894 weakly excites
  22. L15:1589 weakly excites
  23. L16:656 weakly suppresses
  24. L15:232 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 -1.92 and -1.642 values between -1.36 and -1.086 values between -1.08 and -0.8011 values between -0.80 and -0.52265 values between -0.52 and -0.242488 values between -0.24 and 0.041044 values between 0.04 and 0.3260 values between 0.32 and 0.6012 values between 0.60 and 0.887 values between 0.88 and 1.165 values between 1.16 and 1.441 values between 1.44 and 1.722 values between 1.72 and 2.001 values between 3.69 and 3.971 values between 4.25 and 4.531 values between 4.53 and 4.811 values between 9.01 and 9.29offnegativepositiveoften

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. onis
  2. ux
  3. of
  4. igation
  5. favor
  6. iges
  7. aus
  8. den
  9. tô
  10. ationToken

Suppresses

  1. ASIC
  2. /DTD
  3. serialVersionUID
  4. cala
  5. imensional
  6. 或多
  7. 小时内
  8. .UnitTesting
  9. (QObject
  10. 的研究