© 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. 435
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    แห
    -0.10
     Ivory
    -0.10
     Hy
    -0.10
     favour
    -0.10
    /ion
    -0.10
    tic
    -0.09
    -Israel
    -0.09
    '´
    -0.09
    ivas
    -0.09
     Hoffman
    -0.09
     toc
    -0.09
    toc
    -0.09
    OC
    -0.09
     Wah
    -0.09
     wah
    -0.09
    CLUDING
    -0.09
    inkel
    -0.09
     Substance
    -0.08
     Pavel
    -0.08
     hy
    -0.08
    Positive Logits
    (Int
    0.18
    (In
    0.10
    ｡
    0.10
    raki
    0.10
     Ин
    0.10
     इ
    0.10
    347
    0.10
    hoe
    0.09
    件
    0.09
    scp
    0.09
     Garden
    0.09
    ripper
    0.09
    ognito
    0.09
    _CREAT
    0.09
     strncmp
    0.09
     Türkçe
    0.09
    ôt
    0.09
    (IP
    0.09
    ości
    0.09
    seite
    0.09
    Activations Density 47.258%
    Loading dashboard...