© 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. 350
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    urrect
    -0.10
     Mohammed
    -0.10
    enor
    -0.10
    _,,
    -0.09
    erin
    -0.09
    'gc
    -0.09
    hm
    -0.09
    ヌ
    -0.09
    yal
    -0.09
     Pam
    -0.09
     McGr
    -0.09
    isode
    -0.08
    inals
    -0.08
     LCS
    -0.08
    atsby
    -0.08
    aspers
    -0.08
    ldkf
    -0.08
    irt
    -0.08
    omic
    -0.08
    LOBAL
    -0.08
    Positive Logits
    ardown
    0.10
     ske
    0.10
    sock
    0.10
     prol
    0.09
    ぅ
    0.09
    idi
    0.09
     Americ
    0.09
     Sund
    0.09
     Heg
    0.09
     Foster
    0.09
     Bour
    0.09
    zv
    0.09
     Hex
    0.09
    sein
    0.09
    　イ
    0.08
    oun
    0.08
     Burl
    0.08
     Kok
    0.08
    딩
    0.08
    ies
    0.08
    Activations Density 47.811%
    Loading dashboard...