Neuron Explorer

Qwen3-0.6B

"as" in "it seems as if" phrases

A neuron in layer 8 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 "as" when it starts a comparison like "it seems as if" or "it felt as though", the word that sets up an imagined or perceived comparison. When it was turned up, the model drifted into rambling, hesitant sentences about things that seem or feel a certain way.

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

    his book:⏎The two entities that were supposed to write the regulations, the Pay Board and the Price Commission, wrangled and dithered. When it looked as though they were going to miss a crucial deadline

  2. #2 peak

    (the form is at the bottom of the page).⏎Esther – Day 3⏎Xerxes wanted to show off his beautiful wife! But it seems as though he did not give her too much thought until he had drunk too much!

  3. #3 peak

    Frankenstein’s monster, consisting of two identical M1 Max chips bolted together using a silicon interface that serves as a bridge. This clever design makes it seem as if the conjoined chips are in fact just

  4. #4 peak

    because there is seldom just one. In the beginning, actinic keratoses are frequently so small that they are recognized by touch rather than sight. It feels as if you were running a finger over sandpaper. There are many times the number

  5. #5 peak

    y⏎May 27, 2012⏎When the last American astronauts blasted off from the Moon in 1972, it seemed as if they were leaving behind monuments that would stand for all time. On a life

  6. #6 peak

    for she was lovely to look at.⏎As the story continues, pride creeps in.⏎Xerxes wanted to show off his beautiful wife! But it seems as though he didn’t give her too much thought until he had drunk too much!⏎

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 value of 22.3335. I need this value. Answer: 22.3335 34.55 Answer: 22.3335 34

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

    typical limited partnership agreement may provide that a majority vote of the limited partners is necessary for the sale of assets or to remove a general partner. The partnership agreement determines whether the limited partners can vote on these matters.⏎If a limited partner assumes an active

  2. #2 peak

    populate our lives and inform our perceptions of the world. Explore these questions according to the expressions of artists from all over the world. Go beyond Western art to consider where art comes from and how it impacts all of us.⏎Contributors to this open

  3. #3 peak

    ethical caesura in the history of Europe, but there is no consensus when it comes to interpreting it. Some historians trace its origin to Hitler’s radical antis

  4. #4 peak

    . For example, a lake may have a good density of crappie, but few fish over 10 inches. The Preferred Rating tells an angler where to go to for a chance to catch

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. L4:1254 excites
  2. L5:1807 suppresses
  3. L7:1368 excites
  4. L5:2256 suppresses
  5. L6:2313 excites
  6. L7:2058 excites
  7. L7:1795 suppresses
  8. L4:227 weakly suppresses
  9. L5:2026 weakly excites "to" after made or need-type verbs
  10. L4:730 weakly excites
  11. L6:502 weakly suppresses
  12. L5:2209 weakly excites
  13. L4:2051 weakly suppresses
  14. L7:2656 weakly excites
  15. L2:1601 weakly suppresses
  16. L5:1982 weakly excites
  17. L4:1474 weakly excites
  18. L3:2549 weakly suppresses
  19. L2:1963 weakly excites
  20. L5:2889 weakly excites
  21. L3:1390 weakly excites 'that' in 'so that' purpose clauses
  22. L7:2186 weakly suppresses
  23. L1:1857 weakly suppresses
  24. L7:1752 weakly suppresses

Feeds later layers

  1. L9:143 excites
  2. L17:2426 excites 'that' after nouns of belief or fact
  3. L14:2082 excites
  4. L9:288 excites
  5. L18:1389 excites
  6. L13:3 excites
  7. L14:313 excites
  8. L9:330 suppresses gap where a number was removed
  9. L9:75 weakly excites 'what' or 'how' after see or understand
  10. L21:2876 weakly excites
  11. L23:914 weakly excites
  12. L13:2243 weakly excites
  13. L10:707 weakly excites
  14. L18:579 weakly excites
  15. L25:1074 weakly suppresses
  16. L17:2718 weakly excites
  17. L19:1647 weakly excites
  18. L14:830 weakly suppresses
  19. L16:2210 weakly excites
  20. L27:925 weakly suppresses
  21. L16:948 weakly excites
  22. L19:2737 weakly excites
  23. L17:28 weakly excites
  24. L23:197 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 -1.18 and -1.102 values between -1.10 and -1.021 values between -1.02 and -0.941 values between -0.94 and -0.861 values between -0.86 and -0.782 values between -0.78 and -0.703 values between -0.62 and -0.558 values between -0.55 and -0.4711 values between -0.47 and -0.3923 values between -0.39 and -0.3164 values between -0.31 and -0.23176 values between -0.23 and -0.15530 values between -0.15 and -0.071367 values between -0.07 and 0.01994 values between 0.01 and 0.09452 values between 0.09 and 0.17177 values between 0.17 and 0.2558 values between 0.25 and 0.3316 values between 0.33 and 0.417 values between 0.41 and 0.492 values between 0.49 and 0.572 values between 0.65 and 0.732 values between 0.73 and 0.811 values between 0.81 and 0.891 values between 0.97 and 1.051 values between 1.05 and 1.131 values between 1.20 and 1.281 values between 1.44 and 1.521 values between 1.92 and 2.00offnegativepositiveoften

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. that
  2. that
  3. что
  4. tô
  5. →that
  6. 责
  7. _that
  8. ไร
  9. しか
  10. 办

Suppresses

  1. pliers
  2. plier
  3. chool
  4. ounding
  5. inally
  6. endance
  7. opleft
  8. yscale
  9. oops
  10. erval