© 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. 353
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    .scalablytyped
    -0.12
     treff
    -0.11
    imedia
    -0.11
    ayar
    -0.11
    yme
    -0.11
     Pon
    -0.10
    \Lib
    -0.10
     ofType
    -0.10
     Schwe
    -0.10
    imité
    -0.10
     insult
    -0.10
    ColumnsMode
    -0.10
    _notifier
    -0.10
     khắc
    -0.10
    .grpc
    -0.10
     Patty
    -0.10
    orque
    -0.10
     Saud
    -0.10
    _iff
    -0.09
    iano
    -0.09
    Positive Logits
     Wire
    0.10
     Herbert
    0.10
     unp
    0.10
     Dice
    0.10
    ivers
    0.10
     wh
    0.10
    aldi
    0.09
    �
    0.09
     gast
    0.09
     barbar
    0.09
    ess
    0.09
    rary
    0.09
     unl
    0.09
     件
    0.09
     gym
    0.09
    Dice
    0.09
     civ
    0.09
    anned
    0.09
     unr
    0.09
     hap
    0.09
    Activations Density 46.830%
    Loading dashboard...