Neuron Explorer

Qwen3-0.6B

'of' after 'full'

A neuron in layer 1 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 'of' when it comes right after 'full', as in 'full of clay' or 'packed full of'. Turning it up did not produce text about fullness, so the link shows only in the examples.

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

    associations may be buffered by the actual experience of working with ethnic minority students.<|endoftext|>As a gardener facing a yard full of clay, you don't have the luxury of planting without soil preparation. Increase your

  2. #2 peak

    unhappy when you risk losing them. This brain quirk has origins in survival strategies: Imagine you're a hunter-gatherer and you stumble on a pond full of delicious fish. Your dopamine soars and it feels great. You run back to

  3. #3 peak

    to the compost heap⏎Many people overlook the value of dirty washing up water as a compostable commodity. It is very nutrient rich water, full of small food particles and grease. It will help your compost heap degrade quickly, the

  4. #4 peak

    to mind. These are the common recyclable. But of late a new item – cigarette butt – has been added to the list. Used cigarette filters are full of toxins, which can leach into the ground and waterways, damaging living organisms

  5. #5 peak

    chip to replace entire rooms full of computers (Fig. 1).⏎The first microprocessor was the Intel 4

  6. #6 peak

    save your face and your eyes from the harmful rays of the sun.⏎Use swimming goggles⏎The water in swimming pools is full of chlorine, which protects you from germs and infections, but can actually hurt your

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 have been thinking about lately, and I have been thinking about lately. I have been thinking about lately. I have been thinking about lately. I have been thinking about lately. I am not sure if I have been thinking about lately,

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

    and lateral; bracts and bracteoles absent; rays numerous, upwards-spreading, unequal. Calyx teeth obsolete. Petals yellow, obovate, mid rib conspicuous, apex with narrowly inflexed lobule. Sty

  2. #2 peak

    sequence mutations to arise in DNA from the mother or father. The exact mechanism for genome destabilization and how it’s inherited is unknown.⏎Lead author Yuri Dubrova is also cautious about how this data translates to humans. Since most cancer patients are

  3. #3 peak

    way to take advantage of the nutrients that milk provides.⏎The big breakthrough for yogurt came in 1905, when Bulgarian microbiologist Stamen Grigorov discovered the bacteria strain (lactobacillus bulgaricus) that fer

  4. #4 peak

    . But the real number could be ten times higher. The task of estimating the spread of HIV/AIDS in the Czech Republic falls to the Institute's Marie Bruckova, from the National AIDS Reference laboratory:⏎"I wouldn't say this is a huge

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. L0:1301 suppresses
  2. L0:1224 suppresses
  3. L0:178 suppresses
  4. L0:2875 weakly suppresses
  5. L0:1459 weakly excites
  6. L0:2669 weakly excites
  7. L0:2661 weakly excites
  8. L0:44 weakly suppresses
  9. L0:2021 weakly excites
  10. L0:237 weakly suppresses
  11. L0:1195 weakly excites
  12. L0:102 weakly suppresses
  13. L0:407 weakly excites
  14. L0:2374 weakly excites
  15. L0:93 weakly suppresses
  16. L0:2715 weakly excites
  17. L0:2294 weakly excites
  18. L0:119 weakly suppresses
  19. L0:587 weakly excites
  20. L0:2414 weakly suppresses
  21. L0:157 weakly suppresses
  22. L0:107 weakly suppresses newline starting a new block
  23. L0:2148 weakly suppresses
  24. L0:1585 weakly suppresses

Feeds later layers

  1. L3:2094 suppresses "is" after "What" in questions
  2. L2:1238 suppresses
  3. L20:1494 weakly excites
  4. L10:2138 weakly excites
  5. L4:1108 weakly excites
  6. L12:1135 weakly suppresses
  7. L8:2339 weakly suppresses
  8. L13:1360 weakly excites
  9. L22:2623 weakly excites
  10. L6:2731 weakly suppresses
  11. L13:2832 weakly excites "by" after a passive verb
  12. L3:2925 weakly excites
  13. L19:1285 weakly excites
  14. L13:2881 weakly excites
  15. L3:2502 weakly excites
  16. L6:518 weakly excites
  17. L5:2262 weakly suppresses
  18. L15:18 weakly excites
  19. L16:816 weakly excites
  20. L13:2617 weakly excites
  21. L9:1733 weakly excites
  22. L17:1279 weakly excites
  23. L6:1542 weakly suppresses
  24. L16:1235 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.

2 values between -0.58 and -0.502 values between -0.50 and -0.4112 values between -0.41 and -0.3339 values between -0.33 and -0.24124 values between -0.24 and -0.16513 values between -0.16 and -0.071913 values between -0.07 and 0.011018 values between 0.01 and 0.10218 values between 0.10 and 0.1941 values between 0.19 and 0.276 values between 0.27 and 0.363 values between 0.36 and 0.444 values between 0.44 and 0.532 values between 0.53 and 0.612 values between 0.61 and 0.702 values between 0.70 and 0.781 values between 0.87 and 0.951 values between 1.21 and 1.291 values between 1.55 and 1.632 values between 1.80 and 1.892 values between 2.74 and 2.83offnegativepositiveoften

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. alan
  2. itional
  3. ảng
  4. 可以获得
  5. igrams
  6. erd
  7. .functions
  8. 不甘
  9. Hon
  10. ="?

Suppresses

  1. ColumnType
  2. peri
  3. тика
  4. Same
  5. SEP
  6. ',)⏎
  7. ᴗ
  8. 下次
  9. لى
  10. BO