Neuron Explorer

Qwen3-0.6B

capital e starting a word

A neuron in layer 27 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 a capital E that begins a word or acronym, such as Eierbaum, Elysia, EPOCH, Emissivity or EBUS. The strongest negative values are on the letter e in words like Eating and Zero-Emission. Turning it up made the model repeat words like 'modern modern', which is unrelated to the letter.

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

    are called Ostereierbaum (literally: Easter egg tree) and a notable one, decorated since 1965, was the Saalfeld Eierbaum. 2015 was its last year open to the public

  2. #2 peak

    In] Sea Slug Forum. Australian Museum, Sydney. Available from http://www.seaslugforum.net/factsheet/elyscfcang⏎Re: Elysia from Gulf of Mexico⏎From: Kathe R. Jensen, October

  3. #3 peak

    if you have 1000 training examples, you can choose to pick 100 random samples (batch size=100) for each EPOCH (Training cycle)<|endoftext|>|Origin:||co

  4. #4 peak

    the groundwater thus there are significantly reduced mass transfer limitations compared to commonly used gas sparging (bubbling) techniques⏎Practical implications for use of the Waterloo Emitter

  5. #5 peak

    by manufacturer, window type, and age, but some basic information will get you a long way.⏎Please understand that the “e” stands for emissivity. Emissivity is the ability of a material to radiate energy. When heat or

  6. #6 peak

    global vaccine meeting in Nairobi, Kenya. AAP Global Immunization Project Advisory Committee Chair, Meg Fisher, MD, FAAP, served as faculty along with representatives from EAPA, KPA, Gavi, and others organizations. The meeting resulted in

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: why would previous least whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole whole

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

    now Blaze and Logan are at the Smithsonian<|endoftext|>A recent study on high protein has been making the media rounds lately, with some news sites using headlines such as “Eating large amounts of meat, cheese may be as deadly as smoking.”⏎Note:

  2. #2 peak

    government incentive programs available for those who purchase these vehicles. For example, in May of 2019, the Government of Canada implemented a Canada-wide Zero-Emission Vehicle (ZEV) incentive, where customers can receive a rebate when they

  3. #3 peak

    , SpaceX launched a Dragon spacecraft from the Cape Canaveral Air Force Station. The successful flight demonstrated the components necessary to transport humans to low-Earth orbit. SpaceX expects to be ready to fly its first manned mission in

  4. #4 peak

    in the periodic table), the greater the shielding effect is. Essentially, the core electrons shield the valence electrons from the positive charge of the nucleus.⏎Electron-Electron Repulsions ⏎When two electrons are in the same shell, they will

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. L22:2428 excites
  2. L18:221 excites
  3. L17:542 suppresses
  4. L21:435 excites
  5. L17:594 suppresses
  6. L19:645 suppresses
  7. L16:56 suppresses
  8. L2:1749 excites
  9. L17:1717 excites
  10. L6:401 weakly suppresses
  11. L16:829 weakly excites
  12. L10:2401 weakly excites
  13. L15:1272 weakly suppresses
  14. L16:248 weakly excites
  15. L18:139 weakly excites
  16. L16:2851 weakly excites
  17. L3:332 weakly suppresses
  18. L0:1291 weakly suppresses
  19. L15:2839 weakly excites
  20. L11:393 weakly excites
  21. L5:5 weakly excites digit after a label like paper or type
  22. L0:54 weakly excites
  23. L5:1231 weakly excites
  24. L15:1831 weakly excites

Feeds later layers

None: this is the last layer.

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 -43.78 and -42.431 values between -15.39 and -14.041 values between -12.69 and -11.341 values between -11.34 and -9.991 values between -9.99 and -8.644 values between -7.28 and -5.935 values between -5.93 and -4.586 values between -4.58 and -3.238 values between -3.23 and -1.8889 values between -1.88 and -0.533739 values between -0.53 and 0.8340 values between 0.83 and 2.182 values between 2.18 and 3.532 values between 3.53 and 4.884 values between 4.88 and 6.232 values between 6.23 and 7.592 values between 8.94 and 10.29offnegativepositiveoften

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. pared
  2. gnore
  3. 每当
  4. mue
  5. 当之
  6. onNext
  7. 生
  8. elyn
  9. ئ
  10. 孰

Suppresses

  1. thic
  2. ighth
  3. VAL
  4. 終わり
  5. previous
  6. cob
  7. ╚
  8. held
  9. つか
  10. icles