© 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. 504
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    830
    -0.12
     instead
    -0.11
    instead
    -0.11
    /WebAPI
    -0.11
    058
    -0.10
    @nate
    -0.10
    TypeEnum
    -0.10
    vail
    -0.10
    áh
    -0.10
    $MESS
    -0.10
    anches
    -0.10
    оступ
    -0.10
    ęki
    -0.10
     opportunity
    -0.10
    ubu
    -0.10
    edium
    -0.10
    ン�
    -0.10
     tread
    -0.10
    lyn
    -0.10
     chance
    -0.09
    Positive Logits
     Tome
    0.11
    aln
    0.10
     Campo
    0.10
    b
    0.10
    ประส
    0.09
     intelligent
    0.09
    uno
    0.09
    erti
    0.09
     Hansen
    0.09
     Barth
    0.09
    a
    0.09
     sty
    0.09
    ppers
    0.08
     pe
    0.08
    ��
    0.08
     Mushroom
    0.08
     hätte
    0.08
    609
    0.08
     uch
    0.08
     hät
    0.08
    Activations Density 48.780%
    Loading dashboard...