Neuron Explorer

Qwen3-0.6B

words leading into a planned action

A neuron in layer 13 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 lights up on words that set up a purpose or a plan, like 'help teachers [plan]', 'prepare for [rollback]' or 'so they can [accurately] judge'. It fires where the text is about to say what someone will do. Turning it up gave rambling text that did not clearly continue that theme.

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

    is crucial in his effort of making learning meaningful. Moreover, knowing how students learn the English language could help English teachers plan activities suited them. This study generally determined the English language learning strategies of the grade

  2. #2 peak

    Sunday night as Ernesto began to head northwest from Haiti towards Cuba.⏎“It would take a relatively significant change from the current forecast to prevent us from going into rollback preparations,” says launch integration manager LeRoy Cain.⏎Space shuttle officials had planned to decide

  3. #3 peak

    develop a definitive diagnosis, which allows the dental professional to rule out other possible causes of the pain (periodontal disease, caries

  4. #4 peak

    , doctors need to know if you are taking these products so they can accurately judge whether particular symptoms are related to a medical illness or a side effect from an

  5. #5 peak

    consequence of a risk assessment might be included in tender documents so that designers, contractors, subcontractors and suppliers can take them into account when pricing their tenders and planning their work. Ultimately, it may, where relevant, be included in the health

  6. #6 peak

    their students understand the content. Rather than testing what students think they know about the topic, formative assessments allow you to determine how well students comprehend content and guide instruction based on that information.⏎🤔 Challenge: Limited Interaction⏎The lack of interaction between

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 had a new rule after the first 100000 after I had done this, I had done this...? This, I had...? I had done this...? after I had...? This, I had

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

    gluten per day.⏎What Have Other Studies Shown?⏎Overall, studies have delivered inconsistent results in attempting to determine whether early gluten consumption increases the likelihood of developing celiac disease. Previously conducted studies have found that there is no connection between early consumption of

  2. #2 peak

    as possible in my image) my equation was 600/18=33 seconds.⏎With an exposure of 33 seconds I had to have a tripod and a cable release, also with an exposure of 33 seconds

  3. #3 peak

    see if they later developed celiac disease.⏎Additionally, it is important to note that while the study found a relationship between eating more gluten early in life and celiac disease, this relationship is correlational, not causal. This means that the study

  4. #4 peak

    of Healthwise, Incorporated.<|endoftext|>New research is suggesting that children who eat more foods with gluten before the age of two have a greater risk of developing celiac disease if they are genetically predisposed to the condition.⏎This study provides some insight into

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. L11:1350 suppresses
  2. L12:1524 excites
  3. L12:2094 excites
  4. L7:104 excites
  5. L12:2394 suppresses
  6. L11:1508 excites
  7. L12:2113 excites
  8. L12:2274 excites
  9. L11:1367 excites
  10. L7:912 suppresses
  11. L12:732 suppresses
  12. L10:946 suppresses
  13. L12:1463 excites
  14. L12:170 excites
  15. L10:1447 excites
  16. L11:1234 excites
  17. L12:2064 suppresses
  18. L12:833 suppresses
  19. L11:2469 suppresses
  20. L8:840 suppresses
  21. L12:2194 suppresses
  22. L12:1466 weakly suppresses
  23. L7:1860 weakly suppresses
  24. L12:386 weakly suppresses

Feeds later layers

  1. L14:3019 excites
  2. L14:2259 excites
  3. L15:2564 excites
  4. L14:2324 excites
  5. L14:515 suppresses
  6. L14:2323 excites
  7. L15:516 suppresses
  8. L14:2363 excites
  9. L14:1679 excites
  10. L14:1574 suppresses
  11. L15:3001 excites
  12. L14:603 suppresses end-of-document token
  13. L14:582 excites
  14. L15:1383 excites
  15. L14:2601 excites
  16. L14:2486 excites
  17. L14:2863 excites
  18. L14:2875 excites
  19. L14:2451 excites
  20. L18:2975 weakly excites
  21. L15:2562 weakly excites
  22. L21:391 weakly suppresses
  23. L14:457 weakly excites
  24. L14:96 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 -1.76 and -1.651 values between -1.54 and -1.421 values between -1.20 and -1.092 values between -1.09 and -0.982 values between -0.98 and -0.871 values between -0.87 and -0.764 values between -0.76 and -0.659 values between -0.65 and -0.5415 values between -0.54 and -0.4284 values between -0.42 and -0.31274 values between -0.31 and -0.20715 values between -0.20 and -0.091560 values between -0.09 and 0.02787 values between 0.02 and 0.13277 values between 0.13 and 0.2485 values between 0.24 and 0.3528 values between 0.35 and 0.4715 values between 0.47 and 0.588 values between 0.58 and 0.6913 values between 0.69 and 0.806 values between 0.80 and 0.911 values between 0.91 and 1.025 values between 1.02 and 1.131 values between 1.13 and 1.242 values between 1.24 and 1.354 values between 1.35 and 1.472 values between 1.47 and 1.581 values between 1.58 and 1.691 values between 1.80 and 1.911 values between 2.02 and 2.131 values between 2.35 and 2.471 values between 2.58 and 2.69offnegativepositiveoften

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. izzle
  2. accordingly
  3. getReference
  4. Depends
  5. ickness
  6. depending
  7. depends
  8. depended
  9. ере
  10. grew

Suppresses

  1. Bytes
  2. unate
  3. sheets
  4. nung
  5. 斗
  6. mäßig
  7. num
  8. ながら
  9. .rand
  10. ?v