© 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. 405
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    luk
    -0.11
    ันต
    -0.10
    굴
    -0.10
     Manga
    -0.10
    bage
    -0.10
    etooth
    -0.10
    iggins
    -0.10
     genu
    -0.09
     Ders
    -0.09
    役
    -0.09
    feof
    -0.09
    usch
    -0.09
    illin
    -0.09
     Crush
    -0.09
     SEN
    -0.09
    βα
    -0.09
     Poster
    -0.09
    993
    -0.09
    asctime
    -0.09
     thr
    -0.09
    Positive Logits
     scal
    0.11
     TC
    0.10
     cum
    0.10
     FK
    0.10
     count
    0.09
     Draco
    0.09
    弋
    0.09
    adir
    0.09
    count
    0.09
     DV
    0.09
    scal
    0.09
    858
    0.09
    rios
    0.09
     Finance
    0.09
     backstage
    0.08
    949
    0.08
    ught
    0.08
    lob
    0.08
     Wilhelm
    0.08
     definite
    0.08
    Activations Density 53.759%
    Loading dashboard...