Neuron Explorer

Qwen3-0.6B

words for stretching out or extending

A neuron in layer 8 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on words that describe something reaching out across a distance, such as 'extends to', 'stretching to the edge', 'juts out' or 'stretches away'. Turning it up did not produce clearly related writing in the test prompts.

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

    of the ground must be given.⏎From the lofty plateau of the Chersonese, on which the British army was posted, a long ridge of elevated ground extends to the eastward, on the top of which runs the Woronzoff road.

  2. #2 peak

    standing up to the test, but Henry III strengthened the defences further. The outer curtain wall was completed, stretching to the edge of the cliff, and Constable's Gate was constructed - a cluster

  3. #3 peak

    a first floor and a second floor spanning two stories. The outer curtain wall, with twenty individual towers, creates an outer bailey stretching to the edge of the cliff.⏎The Great Tower and forebuilding, viewed from the

  4. #4 peak

    no park to rest the eyes. The Kennicott family home is outdated and stuffy. The prairie, vast and empty, stretches away on every side.⏎Dreams end and realism begins when Carol takes a thirty-minute

  5. #5 peak

    of a doubt that our galaxy has a large bar structure that extends halfway out to the sun’s orbit. We know more about where the Milky Way

  6. #6 peak

    er) to position the⏎arms near the beard, leaving them sticking out in a slightly 3d manner. You⏎can have them sticking straight down, reaching forward, waving, etc

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 a 2020,21,22,23 (L) (M) system. Okay, this is the system, and I am just a user. Okay, this is the system, and I

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

    have a recent version of gcc. m68k-palmos-coff-gcc -v should report its version number to be

  2. #2 peak

    switched communication, which (once circuit is established) allows immediate start of transfer with a guaranteed bit rate. Confusingly, a communication is often synchronous at the physical layer, while being asynchronous at the data link layer.⏎In programming, asynchronous events

  3. #3 peak

    place of WEP pending the availability of the full IEEE 802.11i standard. WPA could be implemented through firmware upgrades on wireless network interface cards designed for WEP that began shipping as far back as 199

  4. #4 peak

    This is quite simple. First, compile (but don't link) each of your .c files, with command lines like the following:⏎m68k-palmos-coff-gcc -g -O2 -c file.c

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. L6:978 suppresses
  2. L6:2836 excites
  3. L7:2307 weakly suppresses
  4. L7:2802 weakly suppresses
  5. L6:1730 weakly suppresses
  6. L4:2989 weakly excites
  7. L5:60 weakly excites
  8. L3:862 weakly suppresses
  9. L5:198 weakly excites unclear: weak "and" in lists
  10. L2:2530 weakly suppresses
  11. L6:1010 weakly suppresses
  12. L5:62 weakly excites
  13. L7:2933 weakly suppresses "from" after hide, shield, or safe
  14. L7:2654 weakly excites
  15. L6:214 weakly excites
  16. L6:1494 weakly suppresses
  17. L2:811 weakly suppresses
  18. L7:278 weakly excites
  19. L3:2750 weakly excites
  20. L7:1040 weakly suppresses
  21. L7:1791 weakly suppresses
  22. L6:2490 weakly excites
  23. L7:1608 weakly excites
  24. L7:2792 weakly excites

Feeds later layers

  1. L10:2980 suppresses
  2. L11:1039 suppresses
  3. L13:2276 excites
  4. L10:1400 suppresses
  5. L16:2602 excites
  6. L9:438 weakly suppresses
  7. L19:3008 weakly excites 'the' or 'outside' after 'cut off from'
  8. L22:3014 weakly excites
  9. L11:3029 weakly suppresses
  10. L13:2851 weakly excites
  11. L16:848 weakly suppresses
  12. L10:2982 weakly suppresses unclear: product and model names
  13. L19:2581 weakly suppresses
  14. L22:2984 weakly excites
  15. L21:79 weakly suppresses
  16. L19:956 weakly excites
  17. L12:299 weakly excites
  18. L11:1073 weakly suppresses
  19. L17:2446 weakly excites
  20. L22:2371 weakly excites
  21. L10:2430 weakly excites
  22. L27:661 weakly suppresses
  23. L9:607 weakly excites
  24. L13:1872 weakly excites comparative or contrasting qualifiers

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.

2 values between -0.89 and -0.801 values between -0.80 and -0.701 values between -0.61 and -0.527 values between -0.52 and -0.4244 values between -0.42 and -0.33156 values between -0.33 and -0.24379 values between -0.24 and -0.15805 values between -0.15 and -0.051307 values between -0.05 and 0.04776 values between 0.04 and 0.14308 values between 0.14 and 0.2378 values between 0.23 and 0.3216 values between 0.32 and 0.416 values between 0.41 and 0.512 values between 0.51 and 0.604 values between 0.60 and 0.696 values between 0.69 and 0.793 values between 0.79 and 0.881 values between 0.88 and 0.971 values between 1.07 and 1.161 values between 1.16 and 1.251 values between 1.25 and 1.351 values between 1.90 and 2.001 values between 2.56 and 2.651 values between 2.74 and 2.84offnegativepositiveoften

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. esis
  2. ilate
  3. inction
  4. tận
  5. orna
  6. pheres
  7. tte
  8. InParameter
  9. tics
  10. émon

Suppresses

  1. type
  2. 是一种
  3. -base
  4. lectic
  5. 存在的
  6. 三种
  7. 类型
  8. 一种
  9. 来源
  10. ooth