© 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. 379
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    �
    -0.10
    ッツ
    -0.10
    stoup
    -0.10
     Gent
    -0.10
    ensch
    -0.09
    ocop
    -0.09
    punk
    -0.09
     Adj
    -0.09
    ха
    -0.09
     gn
    -0.09
    plode
    -0.09
     gent
    -0.09
    QUARE
    -0.09
    dogs
    -0.09
    เหน
    -0.09
     sequ
    -0.09
     GIR
    -0.09
    utf
    -0.09
     Corey
    -0.09
     Gir
    -0.09
    Positive Logits
     Dich
    0.10
    woo
    0.10
     Grinder
    0.09
     Consort
    0.09
     Champagne
    0.09
     Household
    0.09
    ','');↵
    0.09
    917
    0.09
    addock
    0.09
    918
    0.09
    npj
    0.09
     ⌒
    0.09
     wildcard
    0.09
    âl
    0.09
    vet
    0.09
    unal
    0.09
     Bilder
    0.09
     outgoing
    0.09
    TEGER
    0.09
     Clay
    0.09
    Activations Density 47.724%
    Loading dashboard...