© 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. 499
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     gear
    -0.10
    ICLE
    -0.10
     prof
    -0.10
     INTERVAL
    -0.10
    alloca
    -0.09
    ayer
    -0.09
     muscular
    -0.09
    AZY
    -0.09
    071
    -0.09
    /Internal
    -0.09
    icken
    -0.09
     consenting
    -0.09
     champion
    -0.09
     tro
    -0.09
    .Metro
    -0.09
     Benson
    -0.09
    HLT
    -0.09
    шем
    -0.08
     Chill
    -0.08
     Gear
    -0.08
    Positive Logits
    upp
    0.12
     Osman
    0.10
    �
    0.10
    �
    0.10
    raž
    0.10
     grav
    0.10
     Horny
    0.10
     Bowie
    0.10
    oser
    0.10
     Ups
    0.09
     squat
    0.09
     accur
    0.09
    ucha
    0.09
     gamb
    0.09
     bounds
    0.09
    impan
    0.09
     Luna
    0.09
    Attendance
    0.09
    _kv
    0.09
    てい
    0.09
    Activations Density 56.330%
    Loading dashboard...