© 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. 363
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Wax
    -0.12
     IDM
    -0.11
    _unix
    -0.10
    웅
    -0.10
     expend
    -0.10
    ocha
    -0.09
     uns
    -0.09
     Kahn
    -0.09
    GF
    -0.09
    EOF
    -0.09
    cona
    -0.09
    yah
    -0.09
    .future
    -0.09
    Tpl
    -0.09
    duit
    -0.09
    亭
    -0.09
    ALA
    -0.09
     Khan
    -0.09
    τω
    -0.09
    conto
    -0.09
    Positive Logits
     Ende
    0.10
    inent
    0.10
    Forgery
    0.10
    ipher
    0.09
     larg
    0.09
    fffffff
    0.09
     Batt
    0.09
    /Area
    0.09
     Acres
    0.09
     overwhel
    0.09
    lique
    0.09
    Violation
    0.09
    _alive
    0.09
    YC
    0.09
     Diary
    0.09
     Arctic
    0.09
     devour
    0.09
    iola
    0.09
     shower
    0.09
    /lic
    0.09
    Activations Density 44.555%
    Loading dashboard...