© 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. 321
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    cased
    -0.11
     Wen
    -0.10
    Padding
    -0.10
    adil
    -0.10
    aina
    -0.09
     val
    -0.09
    904
    -0.09
    eous
    -0.09
    overe
    -0.09
     ancest
    -0.09
     ment
    -0.09
     Cham
    -0.09
     yola
    -0.09
    wen
    -0.09
    611
    -0.09
    enty
    -0.09
    oscope
    -0.09
     firing
    -0.09
     Henderson
    -0.08
    imos
    -0.08
    Positive Logits
     Hose
    0.11
     SHA
    0.10
     Dahl
    0.09
     DAN
    0.09
    časí
    0.09
    ENV
    0.09
    rels
    0.09
     Gy
    0.09
     buff
    0.09
    SHA
    0.09
    863
    0.09
    zig
    0.09
    ประช
    0.09
    ocommerce
    0.09
    =======
    0.09
    aps
    0.09
    sou
    0.09
    _hooks
    0.09
     Cycle
    0.09
    203
    0.09
    Activations Density 50.465%
    Loading dashboard...