© 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. 421
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    elps
    -0.10
    ácil
    -0.10
     tr
    -0.09
     Hodg
    -0.09
     Kelley
    -0.09
     exh
    -0.09
     se
    -0.09
    fi
    -0.09
     Rena
    -0.09
     fuse
    -0.08
     ren
    -0.08
     resc
    -0.08
     chalk
    -0.08
    reeNode
    -0.08
    fuse
    -0.08
     redd
    -0.08
     Mend
    -0.08
     Cox
    -0.08
    ATCH
    -0.08
    EP
    -0.08
    Positive Logits
    ahir
    0.11
    andi
    0.11
    |i
    0.10
     solidarity
    0.10
     Revel
    0.10
    /／
    0.10
    ideshow
    0.10
     Stateless
    0.10
    utch
    0.10
     Lesser
    0.10
    賢
    0.10
     Bilg
    0.10
    nga
    0.10
    iland
    0.10
    oken
    0.10
    SSIP
    0.09
    .sharedInstance
    0.09
    sip
    0.09
    anker
    0.09
    spy
    0.09
    Activations Density 45.609%
    Loading dashboard...