© 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. 306
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ablo
    -0.12
    onis
    -0.11
     Bon
    -0.10
    beb
    -0.10
    _util
    -0.09
     entr
    -0.09
     Hans
    -0.09
     acc
    -0.09
     Entr
    -0.09
    .uni
    -0.09
    iggins
    -0.09
     programming
    -0.09
    atchet
    -0.09
     投稿
    -0.09
    iswa
    -0.09
     innoc
    -0.09
    empo
    -0.09
    alon
    -0.09
     ryb
    -0.09
     INTERRUPTION
    -0.09
    Positive Logits
     Lump
    0.11
     gim
    0.11
    om
    0.11
     Huffman
    0.09
     depart
    0.09
     Yong
    0.09
     gridColumn
    0.09
     Yar
    0.09
    enberg
    0.09
     stall
    0.09
    ighting
    0.09
     tong
    0.09
     alta
    0.09
    瞬
    0.09
    embr
    0.09
    ivant
    0.09
    CSR
    0.09
    arti
    0.09
     Alta
    0.08
     fast
    0.08
    Activations Density 47.373%
    Loading dashboard...