© 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. 347
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    uyu
    -0.11
     aver
    -0.10
     Vie
    -0.10
    ubic
    -0.10
     Pis
    -0.10
    etail
    -0.09
    ADI
    -0.09
    opleft
    -0.09
     Aus
    -0.09
    .ToShort
    -0.09
     swearing
    -0.09
    ved
    -0.09
     consumers
    -0.09
    ово
    -0.09
     soap
    -0.09
    amb
    -0.09
     Brick
    -0.09
     copp
    -0.09
     trump
    -0.09
    obile
    -0.09
    Positive Logits
    haul
    0.10
    oe
    0.10
    /share
    0.10
     Holmes
    0.10
     global
    0.09
     Corn
    0.09
    .Preference
    0.09
    DDR
    0.09
    _closure
    0.09
    952
    0.09
     sen
    0.09
    iden
    0.09
    êu
    0.09
    妙
    0.09
     ros
    0.09
    .spotify
    0.09
     Handy
    0.09
     resilience
    0.09
    iller
    0.09
     Pier
    0.08
    Activations Density 47.186%
    Loading dashboard...