© 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. 396
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     unp
    -0.10
    egan
    -0.10
     Butt
    -0.10
     Gard
    -0.09
    urtle
    -0.09
     Trom
    -0.08
    crow
    -0.08
     serial
    -0.08
     Tradable
    -0.08
    逸
    -0.08
    ree
    -0.08
    oux
    -0.08
    eday
    -0.08
     interchange
    -0.08
     Powered
    -0.08
    #{@
    -0.08
    латы
    -0.08
     projection
    -0.08
    /projects
    -0.08
    rips
    -0.08
    Positive Logits
     Julius
    0.11
    xeb
    0.11
     Ravens
    0.10
     Ramos
    0.10
    316
    0.09
    vars
    0.09
    ugins
    0.09
     біл
    0.09
     robbed
    0.09
    _iterations
    0.09
     Nixon
    0.09
     Ned
    0.09
     sing
    0.09
    .circular
    0.09
    �
    0.09
    asel
    0.09
     Lav
    0.09
    PIO
    0.09
    obec
    0.09
    937
    0.08
    Activations Density 53.729%
    Loading dashboard...