© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Neuronpedia · MLP Neurons
    5. Llama3.3-70B-IT
    7. MLP Neurons - Layer 21
    9. 408
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    eros
    -0.10
    :::::::
    -0.10
    ┴
    -0.10
     الخط
    -0.10
    823
    -0.09
    osta
    -0.09
    мах
    -0.09
    ater
    -0.09
    еств
    -0.09
    hoa
    -0.09
    ỳ
    -0.08
     Mats
    -0.08
    ossal
    -0.08
    apes
    -0.08
    263
    -0.08
     Gaut
    -0.08
    eneg
    -0.08
    agon
    -0.08
     дот
    -0.08
    Kit
    -0.08
    Positive Logits
     rem
    0.10
    azor
    0.10
     EVT
    0.10
     Beaver
    0.09
     resp
    0.09
    VN
    0.09
    anna
    0.08
     zeit
    0.08
     bout
    0.08
    �
    0.08
    乃
    0.08
    �
    0.08
    мп
    0.08
    417
    0.08
    636
    0.08
     dere
    0.08
    FileSize
    0.08
    ClassLoader
    0.08
     GetEnumerator
    0.08
    illet
    0.08
    Activations Density 48.526%
    Loading dashboard...