© 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. 335
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Pendant
    -0.10
     Pitt
    -0.09
     Florence
    -0.09
     pendant
    -0.09
     haz
    -0.09
     rein
    -0.09
    .object
    -0.09
    514
    -0.09
     Tribune
    -0.09
     comm
    -0.09
     Ragnar
    -0.08
     Lens
    -0.08
     Wesley
    -0.08
     Hanson
    -0.08
     slate
    -0.08
    abcdefghijkl
    -0.08
    NG
    -0.08
     ID
    -0.08
    alex
    -0.08
     Paging
    -0.08
    Positive Logits
    пример
    0.11
    ��
    0.10
     dư
    0.10
    (크기
    0.10
     '{@
    0.09
     unconventional
    0.09
     gratuiti
    0.09
    upro
    0.09
    archy
    0.09
    addtogroup
    0.09
    .scheme
    0.09
    eza
    0.09
     *}
    0.09
    eel
    0.09
     Wine
    0.09
    ायल
    0.09
     голос
    0.09
    uppet
    0.09
    wine
    0.09
    kke
    0.09
    Activations Density 47.008%
    Loading dashboard...