© 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. 315
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     丶
    -0.11
     virgin
    -0.10
    apia
    -0.10
    stp
    -0.10
     ry
    -0.09
     thủy
    -0.09
    igs
    -0.09
    apı
    -0.09
    ITED
    -0.09
    ogy
    -0.09
     autof
    -0.09
     Eng
    -0.09
     dep
    -0.09
    plementation
    -0.09
    /cli
    -0.09
    _PAD
    -0.09
    Ral
    -0.09
    ettle
    -0.09
     trì
    -0.08
    viron
    -0.08
    Positive Logits
     Tale
    0.11
    hurst
    0.11
     Housing
    0.11
    cko
    0.11
    oot
    0.10
     Spl
    0.10
    iston
    0.10
    �
    0.10
    ynom
    0.10
     quam
    0.10
    ariate
    0.10
     sco
    0.09
    iscard
    0.09
    .va
    0.09
     spl
    0.09
    otle
    0.09
    idl
    0.09
     Singleton
    0.09
    ip
    0.09
     Parsons
    0.09
    Activations Density 52.798%
    Loading dashboard...