Neuron Explorer

Qwen3-0.6B

the word 'flat' as adjective

A neuron in layer 4 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 'flat' when it describes a surface, area, or shape, like a flat surface or a flat spiral galaxy. When it was turned up, the text drifted toward surfaces and shapes, though not always in a clearly related way.

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

    are many kinds of digestive enzymes that break down different kinds of food items.<|endoftext|>Chinese architecture started from ancient cave-dwellings, that are still inhabited on the flat yellow plains in varioust parts of Northern China. You ca be sure not to

  2. #2 peak

    A sheep to be measured shall stand on a flat dry surface. Sheep will be shown in its natural fleece (not shorn).⏎

  3. #3 peak

    of Columbia, MO⏎Camera: SBIG ST8300 with FW5⏎Telescope: William Optics FLT110 w/Reducer Flattener IV system @ f5.

  4. #4 peak

    Election pertaining to Blank Electoral College Map 2016 Printable, Source Image : clanrobot.com⏎A map is identified as a counsel, usually with a flat area, of a complete or component of a region. The job of any map

  5. #5 peak

    Desert of Mauritania is easily visible from space because it is nearly 50 kilometers across. Once thought to be an impact crater, the Richat Structure's flat middle

  6. #6 peak

    the bonsai pot. If the soil is dry at this depth, the bonsai tree needs watering.⏎Take your bonsai tree outdoors and set it on a flat surface. Fill a watering can with water and tip the spout downward at a

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 first step in the development of a mixture of... the... is... is... is... is... is... is... is... is... is... is... is... is... is... is... is... is... is... is

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

    The rest of the hole would also receive new soil, not the clay. My theory was that perhaps the roots would grow down as well as out and make the tree stronger. My question is whether the extra digging and new soil was worth the effort

  2. #2 peak

    shallower in heavy clay soils.⏎In some situations, it can be detrimental to amend or replace heavy clay backfill soil, because it can trap water around the tree's roots and also can impede root development.⏎Water will tend to stay in

  3. #3 peak

    ain from fertilizing the shrub from early summer onward to prevent new growth that may be damaged by winter temperatures.⏎Refrain from pruning which can stress the plant and create entry points for disease over the winter.⏎Maintain cool ambient temperatures for

  4. #4 peak

    ground until the soil is warm (65 to 70 degrees F) and the weather has settled. Even a 50-degree night will slow the plant's growth for some time afterwards.⏎You can start basil seeds indoors, three to

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. L3:1042 excites
  2. L3:464 weakly excites
  3. L2:49 weakly suppresses
  4. L3:102 weakly suppresses
  5. L1:364 weakly excites
  6. L2:1657 weakly excites
  7. L3:50 weakly excites
  8. L2:2664 weakly excites
  9. L2:1036 weakly excites
  10. L3:2544 weakly suppresses
  11. L3:691 weakly excites
  12. L2:2328 weakly suppresses
  13. L2:380 weakly suppresses
  14. L3:2725 weakly suppresses
  15. L3:1759 weakly suppresses
  16. L1:2677 weakly suppresses
  17. L3:115 weakly suppresses
  18. L2:506 weakly suppresses
  19. L1:1507 weakly suppresses
  20. L3:59 weakly excites
  21. L3:229 weakly excites
  22. L1:2801 weakly excites
  23. L1:212 weakly suppresses
  24. L2:2258 weakly excites

Feeds later layers

  1. L5:2812 excites
  2. L19:982 weakly suppresses
  3. L7:3043 weakly suppresses
  4. L7:2457 weakly excites
  5. L13:466 weakly suppresses
  6. L19:1893 weakly excites
  7. L21:2700 weakly excites
  8. L10:726 weakly excites
  9. L6:165 weakly excites
  10. L7:1813 weakly excites
  11. L6:166 weakly excites
  12. L24:707 weakly excites
  13. L11:660 weakly excites
  14. L7:1728 weakly suppresses
  15. L5:2891 weakly suppresses
  16. L10:1133 weakly excites
  17. L25:1627 weakly excites
  18. L12:1192 weakly excites
  19. L5:1632 weakly suppresses
  20. L13:2730 weakly excites
  21. L14:2493 weakly suppresses
  22. L7:756 weakly excites
  23. L7:1906 weakly suppresses
  24. L7:2390 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.

2 values between -1.15 and -1.051 values between -1.05 and -0.961 values between -0.78 and -0.691 values between -0.69 and -0.601 values between -0.60 and -0.518 values between -0.51 and -0.4221 values between -0.42 and -0.3379 values between -0.33 and -0.24281 values between -0.24 and -0.15686 values between -0.15 and -0.061429 values between -0.06 and 0.03944 values between 0.03 and 0.12333 values between 0.12 and 0.2188 values between 0.21 and 0.3123 values between 0.31 and 0.404 values between 0.40 and 0.491 values between 0.49 and 0.581 values between 0.58 and 0.671 values between 0.67 and 0.761 values between 1.48 and 1.571 values between 1.94 and 2.031 values between 2.39 and 2.48offnegativepositiveoften

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. flatten
  2. wyjątk
  3. allis
  4. 平坦
  5. Można
  6. Dé
  7. 平整
  8. lokale
  9. кая
  10. exter

Suppresses

  1. ัย
  2. getParam
  3. ited
  4. Min
  5. ический
  6. مة
  7. choices
  8. ⼩
  9. .MinValue
  10. uchos