Neuron Explorer

Qwen3-0.6B

soil and loam

A neuron in layer 4 of Qwen3-0.6B. Its strongest snippets are fairly consistent: several of them peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron reliably lights up on the words for soil and its types, especially 'loam', 'soil' and 'sand, clay and loam'. Turned up, the model's writing kept coming back to soil, though only some of the samples did so. Turned down, it tended to drift toward medical or genetic conditions instead.

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

    plants. Three basic soils are sand, clay and loam. Sand consists mainly of quartz particles, and clay is made up of extremely fine

  2. #2 peak

    how soil is formed.⏎- Recognize that life depends on soil.⏎*See glossary for definations⏎Beakers with water⏎Samples of sand, loam and clay⏎Seeds for planting⏎Toothpicks or forceps⏎

  3. #3 peak

    to our dependence upon soil.⏎- Ask participants to tell you what soil is made of. Invite them to examine the soil samples (sand, loam and clay) under the microscopes.⏎- Bring the class together to discuss what

  4. #4 peak

    Thoughts⏎What Is Soil?⏎The term “soil” comes from the Latin word solis, meaning “ground”. In English,

  5. #5 peak

    include information about the distribution of rock such as limestone, sandstone, coal and granite. Surficial material maps describe deposits that occur above bedrock. This includes soil, but also details up to several hundred feet of deeper unconsolidated material

  6. #6 peak

    ⏎Australia - northern Western Australia, northern Northern Territory, northern Queensland⏎Flats in woodland or vine thicket and on river banks, growing in sand, loam, cracking clay, calcareous or granitic soils; at elevations up

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 a variable is the same as the value of a variable in the table of contents. The value of the variable is a single line. The value of the variable is a single line. The value of the variable is a single

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

    1 in 7,000 births and the risk increases with maternal age. The conditions are associated with severe mental handicap and several physical defects. Most affected individuals die before or soon after birth and they rarely survive beyond the first year of

  2. #2 peak

    in the affected joint. This condition most commonly affects the joints in hips, knees, hands, and spine. Rarely, the

  3. #3 peak

    by mutations in the PTPN11 and RAF1 genes.⏎The symptoms and physical characteristics associated with LEOPARD syndrome are highly variable. However, most affected individuals tend to exhibit characteristic abnormalities of the skin, the structure and function of the

  4. #4 peak

    can cause severe turmoil in a person's physical, psychological, and social health. Eating disorders most commonly affect women and occur in adolescence and young adulthood, though they can occur in anyone,

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. L2:2366 suppresses
  2. L3:1076 weakly suppresses
  3. L0:2073 weakly suppresses
  4. L3:342 weakly excites
  5. L3:2782 weakly excites
  6. L3:1029 weakly suppresses
  7. L3:272 weakly excites
  8. L1:1526 weakly suppresses
  9. L2:2408 weakly suppresses
  10. L3:2140 weakly suppresses
  11. L3:2763 weakly excites
  12. L3:1965 weakly excites
  13. L3:2938 weakly suppresses
  14. L2:2047 weakly excites
  15. L2:2604 weakly excites
  16. L2:49 weakly suppresses
  17. L1:2801 weakly excites
  18. L1:162 weakly excites
  19. L3:464 weakly excites
  20. L3:2077 weakly excites
  21. L0:1301 weakly suppresses
  22. L3:2202 weakly excites
  23. L2:1479 weakly excites
  24. L2:2175 weakly excites

Feeds later layers

  1. L6:1155 excites
  2. L10:2241 excites
  3. L7:1585 excites
  4. L6:2153 excites
  5. L5:1844 excites
  6. L10:3067 excites
  7. L10:1802 weakly excites
  8. L8:1028 weakly suppresses
  9. L5:2300 weakly excites
  10. L11:2813 weakly excites
  11. L6:1503 weakly excites
  12. L7:2927 weakly excites
  13. L5:2809 weakly excites
  14. L9:427 weakly excites
  15. L26:2710 weakly suppresses
  16. L17:1967 weakly suppresses
  17. L27:786 weakly excites
  18. L11:2454 weakly excites
  19. L5:2612 weakly excites
  20. L7:2152 weakly excites
  21. L7:1820 weakly excites
  22. L8:1447 weakly suppresses
  23. L21:1811 weakly suppresses
  24. L24:567 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.

1 values between -4.62 and -4.351 values between -3.55 and -3.291 values between -3.29 and -3.021 values between -1.42 and -1.164 values between -1.16 and -0.891 values between -0.89 and -0.6225 values between -0.62 and -0.36620 values between -0.36 and -0.092785 values between -0.09 and 0.18448 values between 0.18 and 0.449 values between 0.44 and 0.713 values between 0.71 and 0.982 values between 0.98 and 1.242 values between 1.24 and 1.511 values between 1.51 and 1.771 values between 1.77 and 2.041 values between 2.04 and 2.311 values between 2.31 and 2.571 values between 5.77 and 6.04offnegativepositiveoften

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. erre
  2. 堆积
  3. itty
  4. ough
  5. uffy
  6. 以来
  7. youthful
  8. ffective
  9. rede
  10. 沙滩

Suppresses

  1. Vien
  2. iability
  3. uitar
  4. pir
  5. .btnClose
  6. ставил
  7. icone
  8. -vector
  9. icensing
  10. PLICATION