© 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. 342
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    antal
    -0.11
    achen
    -0.11
    ipa
    -0.11
    cntl
    -0.10
    .LookAndFeel
    -0.10
     libertin
    -0.10
    ibri
    -0.10
    incer
    -0.09
    .Offset
    -0.09
     �
    -0.09
     caravan
    -0.09
    腹
    -0.09
    oten
    -0.09
    915
    -0.09
    943
    -0.09
    NOT
    -0.09
    affer
    -0.09
     corre
    -0.09
     Cod
    -0.09
     freder
    -0.09
    Positive Logits
    WSC
    0.10
    oi
    0.10
    onu
    0.10
    buz
    0.09
     Passed
    0.09
     な
    0.09
     omas
    0.09
    step
    0.09
    erk
    0.09
     Whitney
    0.09
    azers
    0.09
    .builders
    0.09
    aju
    0.09
     holders
    0.09
    oin
    0.09
     Toro
    0.09
    oden
    0.09
    ำ
    0.09
     ultimately
    0.09
     Visibility
    0.09
    Activations Density 54.492%
    Loading dashboard...