© 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. 329
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     vag
    -0.11
     suff
    -0.11
     Chill
    -0.10
    MBER
    -0.10
    лава
    -0.10
     chill
    -0.10
    Assets
    -0.10
     lux
    -0.10
    acin
    -0.10
     Chim
    -0.10
    afka
    -0.10
    ahoma
    -0.09
    assen
    -0.09
    oute
    -0.09
    agen
    -0.09
    aben
    -0.09
     Pearson
    -0.09
    ita
    -0.09
    FIELDS
    -0.09
    chl
    -0.09
    Positive Logits
    abis
    0.13
    yre
    0.11
    arms
    0.11
     Trap
    0.11
    ố
    0.11
    anus
    0.11
    �
    0.10
     Humph
    0.10
    /REC
    0.10
    vetica
    0.10
    Trap
    0.10
     traps
    0.10
     Fed
    0.10
     Cra
    0.10
    额
    0.10
    jsc
    0.10
    ynthesis
    0.10
     FS
    0.10
     فرو
    0.10
    urdu
    0.10
    Activations Density 52.805%
    Loading dashboard...