© 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. 415
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ouch
    -0.11
    reen
    -0.11
    ugin
    -0.11
    onus
    -0.10
    yar
    -0.10
     tet
    -0.10
    urance
    -0.10
    loat
    -0.09
    _
    -0.09
    ooks
    -0.09
    onis
    -0.09
     Paula
    -0.09
    ause
    -0.09
    uple
    -0.09
    430
    -0.09
    ule
    -0.09
     Zur
    -0.09
     VIR
    -0.09
     Alv
    -0.08
    iers
    -0.08
    Positive Logits
     cous
    0.11
    ／／
    0.10
    опис
    0.10
    _usec
    0.10
    igo
    0.09
    okes
    0.09
    OperationException
    0.09
     Cous
    0.09
    efined
    0.09
    ahan
    0.09
    ↵↵
    0.09
    　ﾊ
    0.09
    ABCDEFGHI
    0.09
     Call
    0.09
    intree
    0.09
    ntag
    0.09
    굴
    0.09
     �
    0.09
    \db
    0.08
    aru
    0.08
    Activations Density 42.254%
    Loading dashboard...