Neuron Explorer

Qwen3-0.6B

'too' meaning 'also' at clause end

A neuron in layer 8 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 'too' when it means 'also' at the end of a phrase, like 'dangers too' or 'do it too'. It is one of the most consistent word detectors we looked at. Turning it up did not bring out that word in the model's writing.

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

    to your eyes⏎- Remove or reduce eye hazards whenever possible⏎- Know the eye safety dangers at your work and make sure your coworkers are aware of these dangers too⏎- Replace your safety eye wear if it becomes damaged⏎Types of Eye Protection

  2. #2 peak

    to gain control — so a tool isn’t always calling the shots. (We get enough of that in politics, yes?)⏎It’s super easy to get started too.⏎Here’s a quick how-to:⏎- Get in a comfy position. You

  3. #3 peak

    , it becomes our problem too. The Aqua Dental clinic at Pearland assure you to be partners in your child

  4. #4 peak

    . To achieve this, our researchers continually develop state-of-the-art water purification technologies, and now, many of these innovations can be used here on the ground, too. During this webinar, three innovative technologies that were developed at NASA Ames Research Center

  5. #5 peak

    That was before scientists knew about the oceans on moons around other planets, before they knew about how tough microorganisms get here on Earth (and so maybe in space too?), before they started planning experiments to look for life on Mars, and before tech

  6. #6 peak

    the crosshairs of numerous governments for alleged data privacy and national security risks. It is already banned in India, and the US administration is seriously considering banning it too.⏎How can a platform that hosts and displays user-created silly videos be a data

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 power of a position, the value, and the remaining time. It feels like the perfect time to take action. And value is something you can't have, and the remaining time is something you can do, so there's no more

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

    that uses a network or the internet to communicate.⏎User datagram protocol udp is a protocol that sends a datagram in its entirety from the host to the desired destination. Tcp

  2. #2 peak

    audio amplifier have, without a doubt, proved to be more electrically-resilient than their transistor counterparts. When faced by a short or open circuit, valves tend to be protected by their output transformer, whereas transistor-based amplifiers

  3. #3 peak

    and Impedance -- Capacitive"⏎- How out-of-phase AC voltages do not add algebra

  4. #4 peak

    30’s, UHF is an acronym for Ultra High Frequency because at the time 300 MHz was considered high frequency. They can be used when impedance mating is not required.⏎|

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. L7:1908 excites
  2. L4:1458 suppresses
  3. L4:3031 excites
  4. L0:114 weakly excites
  5. L6:2358 weakly suppresses
  6. L6:107 weakly suppresses 'organisms' and 'Code' in reference contexts
  7. L7:2357 weakly suppresses
  8. L6:1825 weakly suppresses
  9. L3:2174 weakly excites
  10. L0:2060 weakly excites
  11. L5:2953 weakly excites
  12. L6:2301 weakly suppresses
  13. L6:2374 weakly excites
  14. L5:2291 weakly excites
  15. L7:2953 weakly excites
  16. L3:1825 weakly suppresses
  17. L1:972 weakly suppresses
  18. L5:1784 weakly suppresses
  19. L2:955 weakly excites
  20. L6:1652 weakly suppresses
  21. L0:2922 weakly excites
  22. L3:50 weakly excites
  23. L6:2288 weakly excites
  24. L6:2523 weakly suppresses

Feeds later layers

  1. L12:2970 excites
  2. L10:696 excites
  3. L11:339 excites the word 'also' before a verb
  4. L18:957 weakly suppresses
  5. L16:2179 weakly excites
  6. L12:2360 weakly excites
  7. L14:1963 weakly excites
  8. L10:2163 weakly excites
  9. L9:1497 weakly excites
  10. L22:1324 weakly excites
  11. L15:2573 weakly excites
  12. L15:220 weakly suppresses
  13. L10:343 weakly suppresses
  14. L10:1058 weakly suppresses
  15. L15:2755 weakly suppresses
  16. L12:1854 weakly suppresses
  17. L10:959 weakly excites
  18. L13:2797 weakly excites
  19. L18:2877 weakly excites
  20. L9:1593 weakly suppresses
  21. L11:1472 weakly excites
  22. L11:583 weakly excites 'both' after a paired subject
  23. L10:1752 weakly excites
  24. L10:2809 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.

3 values between -1.27 and -1.051 values between -1.05 and -0.847 values between -0.84 and -0.6316 values between -0.63 and -0.42329 values between -0.42 and -0.202153 values between -0.20 and 0.011192 values between 0.01 and 0.22146 values between 0.22 and 0.4420 values between 0.44 and 0.6511 values between 0.65 and 0.8610 values between 0.86 and 1.085 values between 1.08 and 1.292 values between 1.29 and 1.501 values between 1.50 and 1.721 values between 1.72 and 1.931 values between 1.93 and 2.141 values between 2.14 and 2.362 values between 2.36 and 2.572 values between 2.57 and 2.781 values between 2.78 and 2.991 values between 2.99 and 3.211 values between 3.21 and 3.421 values between 4.70 and 4.911 values between 7.04 and 7.25offnegativepositiveoften

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. RIA
  2. 了自己的
  3. icism
  4. rin
  5. 了他的
  6. rias
  7. 自己的
  8. themselves
  9. mee
  10. .experimental

Suppresses

  1. Protected
  2. 不动
  3. ablo
  4. sequelize
  5. ắn
  6. aira
  7. orque
  8. aler
  9. 开盘
  10. unks