Neuron Explorer

Qwen3-0.6B

'of' after 'think' or 'out'

A neuron in layer 0 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' when it comes right after phrases like 'Think of' or 'way out of'. Turning it up did not produce any obvious change in the writing's theme.

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

    're looking to help the bees in your hood, consider adding some native flowering plants to your garden.⏎"Think of the flowers your grandmother used in her garden as a practical guide, especially when using

  2. #2 peak

    and use in sentences; and questions for both literary analysis and critical reading. Each week the student is challenged to "make it real." For instance: "Think of two examples of foils in literature or movies" or "Name at least one

  3. #3 peak

    write a setting description.⏎Below is a picture of the outside appearance of the lighthouse. There is also a picture of the inside of a lighthouse. Think of interesting words to describe the looks and feel of the lighthouse. If you can

  4. #4 peak

    a success?⏎19. It can’t be spring if your heart is filled with past failures.⏎20. Don’t think of it as failure. Think of it as time-released success.⏎21. There are no failures. Just

  5. #5 peak

    memories with a computer. An Imagination Interface, perhaps. By any name, it doesn’t take much time to realize that you have always wanted one. Think of a world where you could selectively download your life’s memories- sights, sounds,

  6. #6 peak

    _t;⏎This type is used to define difference between two pointers. Depending on which of the pointers is larger, this value may be positive or negative.<|endoftext|>Think of your body like a car. Where the muscles are the shock systems and the skeleton

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: I am thinking about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about about

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

    health workers are battling to save lives in the midst of shortages of personal protective equipment, oxygen, and treatments.⏎“Vaccines have never been the way out of this crisis on their own, but this current wave is demonstrating again just what a

  2. #2 peak

    planetary security forces. Almost every smugglers vessel had improved light speed and sub-light speed drives for increased speed as well as boosted weapons systems to fight their way out of tough situations. Another of the most prevalent modifications to a smugglers freighter were

  3. #3 peak

    member’s home or the Women's Center shelter.⏎• Keep the Women's Center toll-free hotline phone number close at hand.⏎• Figure out the quickest way out of your home and practice the escape.⏎• Obtain an Order of Protection.⏎• Pack

  4. #4 peak

    scope, abundance, it is because he has inherited the achievements of his forerunners. Nothing warrants the idea that he will ever hew his way out of the half-knowledge half-ignorance which is the stamp of his kind

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

None: this is the first layer.

Feeds later layers

  1. L18:778 excites
  2. L22:1031 weakly excites
  3. L22:2705 weakly excites
  4. L23:2959 weakly suppresses
  5. L26:1089 weakly excites
  6. L20:3008 weakly excites
  7. L20:392 weakly excites
  8. L1:420 weakly suppresses
  9. L19:595 weakly suppresses
  10. L18:110 weakly excites
  11. L21:1060 weakly excites
  12. L20:1962 weakly suppresses
  13. L8:857 weakly excites
  14. L23:309 weakly excites
  15. L12:2771 weakly suppresses
  16. L20:2681 weakly excites
  17. L6:346 weakly suppresses
  18. L6:1782 weakly excites 'of' after a category noun
  19. L22:384 weakly excites
  20. L2:3052 weakly excites
  21. L20:2414 weakly excites
  22. L27:797 weakly excites
  23. L27:2806 weakly excites
  24. L12:2053 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 -1.58 and -1.521 values between -0.87 and -0.801 values between -0.80 and -0.742 values between -0.67 and -0.611 values between -0.61 and -0.544 values between -0.54 and -0.483 values between -0.41 and -0.359 values between -0.35 and -0.2824 values between -0.28 and -0.2270 values between -0.22 and -0.15250 values between -0.15 and -0.09770 values between -0.09 and -0.022233 values between -0.02 and 0.04362 values between 0.04 and 0.11102 values between 0.11 and 0.1731 values between 0.17 and 0.2414 values between 0.24 and 0.3010 values between 0.30 and 0.375 values between 0.37 and 0.431 values between 0.43 and 0.504 values between 0.50 and 0.563 values between 0.56 and 0.632 values between 0.63 and 0.691 values between 0.69 and 0.762 values between 0.82 and 0.891 values between 0.89 and 0.961 values between 0.96 and 1.02offnegativepositiveoften

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. yssey
  2. emailer
  3. Observatory
  4. INTR
  5. umo
  6. ample
  7. lico
  8. PRS
  9. transform
  10. ROUP

Suppresses

  1. benh
  2. /pp
  3. Arbor
  4. ッシュ
  5. rear
  6. usted
  7. 建成
  8. illation
  9. 螂
  10. sizes