Neuron Explorer

Qwen3-0.6B

'iv' inside herbivores, energy fuel words

A neuron in layer 8 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 fires on the piece 'iv' in the middle of the word 'herbivores', and on a few other odd word fragments. It is pulled the other way by text about burning fat or energy for fuel. Turning it up did not produce any clear change in topic.

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

    which biotic and abiotic drivers are redefining the distributional dynamics of native and non-native plants under global change.⏎Current study system. Plants and herbivores! Plants may seem like static

  2. #2 peak

    ., Filippi, A., & Marini, L. (2021). Contrasting response of native and non‐native plants to disturbance and herbivory in mountain environments. Journal of Biogeography, 48(7

  3. #3 peak

    -scale reshuffling of species distributions creates novel interactions among species and across trophic levels that previously did not co-occur. In particular, interactions with herbivores emerged as a fundamental driver of plant community

  4. #4 peak

    human disturbance, while the same drivers promote non-native spread. Although biotic interactions should modulate plant invasions, it is still unclear how invertebrate herbivores can affect non-native spread. Most previous research focused on lab experiments, and

  5. #5 peak

    birds, and other herbivores that like to snack on fruits, leaves, and flowers. But what W

  6. #6 peak

    cheese filling. The turnover is grilled or fried, using either flour or a corn tortilla. Served with guacamole and sour cream, this simple unleavened flatbread turnover remains a favorite snack of the Mexican and Tex-Mex cuisine

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: 100 g of food is used to produce 200 kcal of energy. How many grams of carbohydrates are consumed? The given data: - 100 g of food is used to produce 20

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

    When your cells can’t get glucose (a kind of sugar) to burn for energy, they burn fat instead. This leaves behind acids called ketones in your blood and urine. A

  2. #2 peak

    collision that took place 1.3 billion years ago. When it occurred, about three times the mass of the sun was converted to energy in a fraction of a second.⏎The discovery has been accepted for publication in Physical

  3. #3 peak

    Restricting calories causes muscles to rely more on glucose from the food you’re consuming for energy than from the stored fat. They also become more efficient.⏎Many of these hormones don’t return to normal

  4. #4 peak

    calorie burn:⏎- RMR=resting metabolic rate-the amount of calories you need to exist without any activity-ie:bedrest⏎- TEA-thermic effect of activity-this, obviously, represents the caloric burn of activity, both

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. L6:1181 suppresses
  2. L6:1935 weakly excites
  3. L6:1832 weakly suppresses
  4. L6:2465 weakly excites
  5. L3:2958 weakly excites
  6. L7:1914 weakly suppresses
  7. L5:1042 weakly suppresses
  8. L6:2691 weakly excites
  9. L2:2460 weakly suppresses
  10. L2:493 weakly suppresses
  11. L5:342 weakly suppresses line breaks inside wrapped sentences
  12. L7:1832 weakly suppresses
  13. L7:1590 weakly suppresses
  14. L7:76 weakly excites
  15. L0:1301 weakly suppresses
  16. L3:651 weakly suppresses zero in dates inside URLs
  17. L0:1677 weakly suppresses
  18. L4:882 weakly excites 'with' after provide or familiarize
  19. L6:1678 weakly excites
  20. L7:2463 weakly excites
  21. L5:1917 weakly suppresses 'to' after 'what' or 'where' (what to do)
  22. L6:2456 weakly excites
  23. L6:1921 weakly excites
  24. L7:303 weakly suppresses

Feeds later layers

  1. L21:2922 suppresses
  2. L20:3023 weakly excites
  3. L18:2854 weakly suppresses
  4. L10:983 weakly suppresses
  5. L9:2709 weakly excites
  6. L25:722 weakly suppresses
  7. L21:980 weakly suppresses
  8. L18:969 weakly suppresses
  9. L19:2679 weakly excites
  10. L10:865 weakly suppresses
  11. L20:1898 weakly suppresses
  12. L10:628 weakly excites
  13. L11:2847 weakly excites
  14. L10:2187 weakly excites
  15. L11:2448 weakly excites
  16. L23:1859 weakly suppresses
  17. L9:2612 weakly suppresses
  18. L15:1445 weakly suppresses
  19. L25:1379 weakly excites
  20. L19:1926 weakly suppresses
  21. L21:2521 weakly suppresses
  22. L10:861 weakly suppresses
  23. L11:1382 weakly suppresses
  24. L21:2035 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 -5.74 and -5.571 values between -5.22 and -5.051 values between -4.70 and -4.531 values between -2.96 and -2.792 values between -2.62 and -2.443 values between -1.75 and -1.571 values between -1.40 and -1.232 values between -1.23 and -1.051 values between -1.05 and -0.884 values between -0.88 and -0.7116 values between -0.53 and -0.36218 values between -0.36 and -0.181400 values between -0.18 and -0.011732 values between -0.01 and 0.16422 values between 0.16 and 0.3485 values between 0.34 and 0.5113 values between 0.51 and 0.693 values between 0.69 and 0.861 values between 0.86 and 1.031 values between 1.03 and 1.21offnegativepositiveoften

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. 湿润
  2. anging
  3. tí
  4. ometers
  5. athroom
  6. WARDS
  7. typingsJapgolly
  8. filtro
  9. 妇联
  10. ocrats

Suppresses

  1. massa
  2. 燃料
  3. 重整
  4. igne
  5. 合成
  6. 原料
  7. 能量
  8. 化石
  9. energy
  10. 功