© 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. 492
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    -0.12
     dep
    -0.12
     marsh
    -0.11
     Lords
    -0.11
    aren
    -0.10
     pac
    -0.10
     full
    -0.10
     Pac
    -0.10
    akit
    -0.10
    aket
    -0.09
     mod
    -0.09
    owl
    -0.09
     Francis
    -0.09
    esc
    -0.09
    ese
    -0.09
     Drag
    -0.09
     nob
    -0.09
     floor
    -0.08
     crown
    -0.08
     DL
    -0.08
    Positive Logits
    év
    0.13
    _utilities
    0.12
    .IsNullOr
    0.12
    itaire
    0.11
     Evo
    0.11
    捷
    0.11
    hya
    0.11
     overs
    0.11
    abr
    0.11
    ceptar
    0.11
    획
    0.11
    下载次数
    0.10
    tet
    0.10
    idia
    0.10
    touches
    0.10
    daş
    0.10
     Rhodes
    0.10
     Yön
    0.10
    жу
    0.10
    _renderer
    0.10
    Activations Density 51.134%
    Loading dashboard...