Neuron Explorer

Qwen3-0.6B

'to' after 'have got' or 'will have' (obligation)

A neuron in layer 4 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 'to' when it follows 'have', 'has got', or 'will have' and introduces something that must be done, like 'will have to move' or 'has got to be created'. It is a clear and consistent pattern. When turned up, the model sometimes wrote about needing to do things, though this was not consistent.

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

    to be at a disadvantage for heat loss,” Hindle explained. “They’re more likely to lose heat to the environment, and therefore they’re going to have to ramp up heat production.”⏎The three-year grant from the National Science Foundation’s Division

  2. #2 peak

    . Even if you don't make it all the way to the top of the mountain or hike all 40 miles of the trail, you'll have to hike just to get back to civilization. Unless you quit within the first mile or

  3. #3 peak

    solution to increase food and could be one of the next most important developments in human history. By 2050, the edible bioresource biomass will have to satisfy the 9 billion people predicted to live on the planet. Seaweed

  4. #4 peak

    that you can have whatever you want whenever you want without having to work for it. It is about being convinced that you deserve things you want and someone has got to give them to you no matter what.⏎Below are what I believe are some of

  5. #5 peak

    A checklist for evaluating would-be donors and fully explaining the risks — plus requirements to better monitor those donors' health and social stability for two years. Centers would have to track such

  6. #6 peak

    , adaptable, and easily taught.⏎“The social relationships [between] these things matter a lot. And these things have got to be created, developed, made to be sustainable as much as the tech,” R

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 number of a certain type of object, and the number of other types of objects in the world, and the world is known as the number of the people. The world is the number of the people, and the number of the people

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

    report:<|endoftext|>Marketing is related to the exchange of goods and services. Through its medium the goods and services are brought to the place of consumption. This satisfies the needs of the customers. The following activities are undertaken in respect of the exchange of goods

  2. #2 peak

    buddy’ and ‘bro’ in the OED have recently been revised. We explore their history and increase in popularity.<|endoftext|>NEED FOR ASSISTANCE⏎People with autism needed assistance with a range of activities, with

  3. #3 peak

    help the students to develop and understand the concept of child health, the trends in child care and health problems of children. It will enable the students to meet the needs of the children, in health and sickness.⏎This course book is designed for students

  4. #4 peak

    develop a database for historical analysis. It provides an ingenious and elaborate instrument to process, record, and analyze any type of historical data and sources. Its use demands a

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. L0:2662 excites
  2. L3:266 weakly suppresses
  3. L3:1787 weakly suppresses
  4. L2:2739 weakly suppresses
  5. L2:449 weakly excites
  6. L3:2760 weakly excites
  7. L2:2918 weakly suppresses
  8. L0:1592 weakly suppresses 'Springer' and 'rebirth' style word pieces
  9. L2:1494 weakly suppresses
  10. L2:2640 weakly suppresses
  11. L0:1671 weakly suppresses
  12. L1:1641 weakly suppresses
  13. L3:2822 weakly excites
  14. L1:2801 weakly excites
  15. L2:1548 weakly suppresses
  16. L2:126 weakly excites
  17. L1:2173 weakly suppresses
  18. L1:2497 weakly excites
  19. L2:2328 weakly suppresses
  20. L1:2127 weakly suppresses
  21. L3:2843 weakly excites
  22. L3:50 weakly excites
  23. L0:2834 weakly excites
  24. L3:2154 weakly suppresses

Feeds later layers

  1. L16:2349 strongly excites
  2. L10:520 excites
  3. L17:2345 excites
  4. L9:640 excites
  5. L17:1822 excites 'should' in advice and claims
  6. L16:2563 excites
  7. L5:2538 excites
  8. L17:451 excites
  9. L6:2182 excites
  10. L10:1576 excites
  11. L7:1232 excites
  12. L14:2124 excites
  13. L21:2252 excites
  14. L10:562 excites
  15. L7:3004 excites
  16. L5:1846 excites
  17. L21:3062 excites
  18. L5:1701 excites
  19. L20:2529 excites
  20. L24:2712 weakly excites
  21. L18:2568 weakly excites
  22. L8:1465 weakly excites
  23. L20:2395 weakly excites
  24. L25:1092 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 -1.18 and -0.923 values between -0.92 and -0.6764 values between -0.67 and -0.41678 values between -0.41 and -0.162931 values between -0.16 and 0.10213 values between 0.10 and 0.358 values between 0.35 and 0.612 values between 0.61 and 0.861 values between 0.86 and 1.121 values between 1.12 and 1.372 values between 1.37 and 1.631 values between 1.88 and 2.141 values between 2.14 and 2.391 values between 6.22 and 6.471 values between 8.77 and 9.02offnegativepositiveoften

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. обязательно
  2. 不得不
  3. obliged
  4. must
  5. слав
  6. require
  7. ACM
  8. 必须
  9. opers
  10. 就必须

Suppresses

  1. représent
  2. etable
  3. สบาย
  4. uation
  5. setMessage
  6. tings
  7. numeros
  8. ispers
  9. setResult
  10. uations