© 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. 366
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    mé
    -0.10
     Maz
    -0.10
    alm
    -0.10
     cu
    -0.10
     Titanic
    -0.09
     rap
    -0.09
     Barbar
    -0.09
    ustos
    -0.09
    itude
    -0.09
    ги
    -0.09
    ium
    -0.09
    hoa
    -0.09
    ovat
    -0.09
    gow
    -0.09
    HO
    -0.08
    -Identifier
    -0.08
     scenery
    -0.08
    čan
    -0.08
     Yellow
    -0.08
    viders
    -0.08
    Positive Logits
    antt
    0.10
    onen
    0.09
    zs
    0.09
    ?option
    0.09
     Sour
    0.09
     flush
    0.09
    /**↵↵
    0.09
    _symbols
    0.09
    Flush
    0.09
     mandated
    0.09
     hosts
    0.09
    icao
    0.09
     Flush
    0.09
     Stereo
    0.08
     hast
    0.08
     Absolute
    0.08
    串
    0.08
    undi
    0.08
     usher
    0.08
    .poster
    0.08
    Activations Density 52.372%
    Loading dashboard...