Neuron Explorer

Qwen3-0.6B

'to' after 'need' in 'what you need to know'

A neuron in layer 5 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 'to' in phrases like 'everything you need to know' or 'what you need to get started'. It goes quiet, and slightly negative, on 'do' or 'with' in 'what does this have to do with'. Turning it up didn't produce a clear theme in the sample text.

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

    the complexity of the case and what needs to be achieved in the movement of the patient's teeth. A palatal expander

  2. #2 peak

    setting. This repair method⏎The above information equips you with everything you need to know about FCAW as a new welder. The techniques and advantages and

  3. #3 peak

    if done correctly, but there are a few things you need to know before starting. Keep reading to learn more about how long composting takes and what you need to get started!⏎How Long Does It Take To Break Compost Down?⏎This is

  4. #4 peak

    . They support teachers by providing a map of progression from Graduate through Proficient and Highly Accomplished to Lead teacher. They help teachers work out what they need to learn in order to become the kinds

  5. #5 peak

    right ratio to get perfect composting results. Compostable materials are divided into browns and greens and must be added carefully. This article discusses everything you need to know about composting ratio and how it affects the process.⏎Carbon to Nitrogen

  6. #6 peak

    What would need to happen? What would I need to have?”⏎For many people, the answer lies in having what someone else has

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: is it related to the internet? What is the connection between the internet and the previous mention of the time of the virus? What is the connection between the internet and the previous mention of the time of the virus? What is the connection between

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

    to produce structures that are more efficient to run, cutting ongoing costs and minimizing the carbon footprint.⏎What does this have to do with BrightBuilt Barn?⏎Well, it turns out that the Barn was also designed

  2. #2 peak

    does. Methane gas (CH4) traps about 34 times more heat within the earth’s atmosphere.⏎So what does worm manure have to do with dog waste?⏎Well, dog waste is not just full of bacteria that causes disease

  3. #3 peak

    components of the Pie Model in the Ruler vs. Pie Concept.⏎Webster defines Truth as Reality. But reality to whom? (What does this have to do with consumer research? We will get to that later.) We have often heard the

  4. #4 peak

    Parkinson’s Australia Inc., 2014). Recognising these signs and symptoms can aid early diagnosis and slow disease progression.⏎What’s dopamine got to do with it?⏎Dopamine is often referenced as the chemical in our brain that

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. L4:538 suppresses
  2. L1:1229 weakly excites
  3. L2:586 weakly suppresses
  4. L3:25 weakly suppresses
  5. L4:2787 weakly suppresses
  6. L4:207 weakly excites
  7. L3:1274 weakly suppresses
  8. L2:410 weakly suppresses
  9. L4:25 weakly excites
  10. L0:547 weakly excites
  11. L2:2267 weakly excites
  12. L4:2048 weakly suppresses
  13. L0:2822 weakly excites
  14. L0:526 weakly excites
  15. L4:2168 weakly excites
  16. L0:1096 weakly suppresses
  17. L3:717 weakly suppresses
  18. L4:37 weakly suppresses
  19. L4:1555 weakly excites
  20. L4:1119 weakly excites
  21. L4:2345 weakly suppresses
  22. L2:655 weakly suppresses
  23. L4:1052 weakly excites
  24. L2:2343 weakly excites

Feeds later layers

  1. L10:2075 suppresses
  2. L15:2494 suppresses
  3. L12:2737 suppresses
  4. L12:791 suppresses
  5. L24:1877 weakly suppresses
  6. L16:173 weakly suppresses
  7. L11:2286 weakly suppresses
  8. L8:1065 weakly suppresses
  9. L11:1173 weakly suppresses
  10. L15:2393 weakly excites
  11. L9:1737 weakly suppresses
  12. L6:2880 weakly suppresses
  13. L11:2253 weakly excites
  14. L6:201 weakly excites
  15. L18:684 weakly suppresses
  16. L12:1193 weakly suppresses
  17. L17:2403 weakly suppresses
  18. L7:1763 weakly suppresses
  19. L23:1625 weakly excites
  20. L8:1890 weakly suppresses
  21. L12:1637 weakly excites
  22. L14:871 weakly suppresses
  23. L12:1625 weakly excites
  24. L20:1937 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 -1.94 and -1.852 values between -1.76 and -1.662 values between -1.66 and -1.572 values between -1.57 and -1.481 values between -1.39 and -1.302 values between -1.21 and -1.114 values between -1.11 and -1.022 values between -1.02 and -0.931 values between -0.84 and -0.751 values between -0.75 and -0.664 values between -0.66 and -0.565 values between -0.56 and -0.4713 values between -0.47 and -0.3853 values between -0.38 and -0.29160 values between -0.29 and -0.20428 values between -0.20 and -0.111080 values between -0.11 and -0.011411 values between -0.01 and 0.08483 values between 0.08 and 0.17160 values between 0.17 and 0.2650 values between 0.26 and 0.3514 values between 0.35 and 0.4511 values between 0.45 and 0.543 values between 0.54 and 0.634 values between 0.63 and 0.721 values between 0.72 and 0.812 values between 0.81 and 0.902 values between 0.90 and 1.001 values between 1.00 and 1.091 values between 1.09 and 1.181 values between 1.18 and 1.271 values between 1.27 and 1.361 values between 1.45 and 1.551 values between 1.64 and 1.73offnegativepositiveoften

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. oui
  2. acro
  3. 最强
  4. unconditional
  5. unami
  6. -strong
  7. minimum
  8. strongest
  9. 坚强
  10. vars

Suppresses

  1. idden
  2. ạc
  3. 肤色
  4. 的文化
  5. 摛
  6. karış
  7. matrices
  8. ancest
  9. _matrices
  10. 的一面