© 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. 475
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    unal
    -0.12
    .heroku
    -0.12
     sobě
    -0.11
    lapping
    -0.11
     TP
    -0.10
    agus
    -0.10
     Kitty
    -0.10
    益
    -0.10
     Expl
    -0.10
     notifier
    -0.10
    eros
    -0.09
     refr
    -0.09
     FP
    -0.09
    jectories
    -0.09
    oons
    -0.09
     Gust
    -0.09
    .localization
    -0.09
     offic
    -0.09
    azer
    -0.09
    .eth
    -0.09
    Positive Logits
     objects
    0.16
     inflamm
    0.12
     Dame
    0.12
     everything
    0.11
    chwitz
    0.11
    orea
    0.10
    objects
    0.10
    ��
    0.10
    244
    0.10
    794
    0.10
     discrimin
    0.10
     hoa
    0.10
    hek
    0.10
    urovision
    0.10
     object
    0.10
     objetos
    0.10
     Pussy
    0.10
     allem
    0.09
     Everything
    0.09
     Commissioner
    0.09
    Activations Density 55.644%
    Loading dashboard...