© 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. 459
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     GW
    -0.10
     �
    -0.10
    lookup
    -0.09
     Bakan
    -0.09
     GSM
    -0.09
     Olsen
    -0.09
    Wrapped
    -0.09
    habi
    -0.09
     SMB
    -0.09
    uzey
    -0.09
     Screw
    -0.09
    aret
    -0.09
     Kro
    -0.09
     hairy
    -0.09
     Lage
    -0.09
     PR
    -0.08
     Harness
    -0.08
     screw
    -0.08
     Guides
    -0.08
    strcasecmp
    -0.08
    Positive Logits
    ipl
    0.12
    /process
    0.11
    _given
    0.10
     sag
    0.10
     Encoding
    0.10
     mon
    0.10
    _NC
    0.10
    eries
    0.10
    Enumerator
    0.10
    xious
    0.10
    ้้
    0.10
    plit
    0.10
    oplayer
    0.10
    irk
    0.10
    olds
    0.09
    eni
    0.09
    _LD
    0.09
     puzz
    0.09
    ายน
    0.09
    tuk
    0.09
    Activations Density 49.808%
    Loading dashboard...