© 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. 365
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    enville
    -0.11
    uber
    -0.11
    öt
    -0.10
    erin
    -0.09
    จร
    -0.09
     inters
    -0.09
    ittance
    -0.09
     Ari
    -0.09
    authorized
    -0.09
    elo
    -0.09
     lag
    -0.09
    Leaf
    -0.09
    amo
    -0.08
    Tab
    -0.08
     minority
    -0.08
     Wilde
    -0.08
     Lag
    -0.08
     plural
    -0.08
    ussy
    -0.08
     dick
    -0.08
    Positive Logits
    marsh
    0.11
     hal
    0.11
    mast
    0.11
     biz
    0.11
     Alien
    0.11
    ozilla
    0.10
    ippy
    0.10
    ikh
    0.10
    Periph
    0.10
    ��
    0.10
    Biz
    0.10
    pNet
    0.10
     Hoch
    0.10
    .reactivex
    0.10
    alien
    0.09
    isko
    0.09
    zos
    0.09
    irtual
    0.09
    ponder
    0.09
     kicker
    0.09
    Activations Density 48.779%
    Loading dashboard...