© 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. 439
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    INGLE
    -0.09
     rast
    -0.09
     Slots
    -0.09
    lands
    -0.08
    817
    -0.08
     aforementioned
    -0.08
    607
    -0.08
     Alv
    -0.08
    aller
    -0.08
    ->__
    -0.08
    ands
    -0.08
    сам
    -0.08
    clip
    -0.08
     Kok
    -0.08
    506
    -0.08
    ery
    -0.08
     рев
    -0.08
     Constantin
    -0.08
    hev
    -0.08
    chez
    -0.08
    Positive Logits
    №№
    0.12
    ohana
    0.11
     kariy
    0.10
    надлеж
    0.10
    aN
    0.10
     Latter
    0.10
    /an
    0.10
     Tro
    0.10
    oS
    0.09
    >NN
    0.09
    ErrMsg
    0.09
     backing
    0.09
     Pee
    0.09
    itoris
    0.09
     TIMEOUT
    0.09
    assic
    0.09
    Архів
    0.09
    (크기
    0.09
    ��
    0.09
    iVar
    0.09
    Activations Density 58.123%
    Loading dashboard...