© 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. 443
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Herrera
    -0.11
     Eag
    -0.09
     Hu
    -0.09
    _dyn
    -0.09
     Downs
    -0.09
     hu
    -0.09
     Petro
    -0.09
    出口
    -0.09
    čky
    -0.08
    ooth
    -0.08
     Kerr
    -0.08
     �
    -0.08
     Asset
    -0.08
     Loft
    -0.08
    (木
    -0.08
    ament
    -0.08
    illy
    -0.08
    远
    -0.08
    reds
    -0.08
    atz
    -0.08
    Positive Logits
     whom
    0.10
    enek
    0.10
    arius
    0.09
     ゝ
    0.09
     carbon
    0.09
     Juda
    0.09
    OfDay
    0.09
    ivr
    0.09
    yal
    0.09
     Carbon
    0.08
    vig
    0.08
    ukan
    0.08
    isans
    0.08
    .stub
    0.08
     puls
    0.08
    덕
    0.08
     sin
    0.08
    突
    0.08
    aku
    0.08
    _party
    0.08
    Activations Density 49.008%
    Loading dashboard...