© 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. 311
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    atter
    -0.10
    oha
    -0.10
    nech
    -0.10
    PN
    -0.10
     Brut
    -0.10
     cảnh
    -0.09
     Farrell
    -0.09
     Emanuel
    -0.09
     Made
    -0.09
     referenced
    -0.09
     Guest
    -0.09
    antic
    -0.09
     Bris
    -0.09
    unch
    -0.09
     Kop
    -0.09
     unread
    -0.09
     stake
    -0.09
     stakes
    -0.09
    �
    -0.09
     cele
    -0.09
    Positive Logits
    ipeg
    0.11
    寸
    0.10
    edImage
    0.10
     Clement
    0.10
     reim
    0.10
    igans
    0.10
    陵
    0.10
    arty
    0.10
    edList
    0.10
    ivr
    0.09
    BOOT
    0.09
    ンブ
    0.09
    Wins
    0.09
     der
    0.09
     плен
    0.09
     Wildlife
    0.09
    \Migration
    0.09
    estro
    0.09
    orex
    0.09
    coli
    0.09
    Activations Density 49.162%
    Loading dashboard...