© 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. 482
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    iks
    -0.11
    �
    -0.10
    司
    -0.10
     Quit
    -0.10
     Trafford
    -0.10
     Kens
    -0.10
     Romero
    -0.10
     Jou
    -0.10
     Prostit
    -0.10
    llu
    -0.10
    ikit
    -0.10
    onica
    -0.10
    우리
    -0.09
    quel
    -0.09
    dek
    -0.09
    �
    -0.09
     temperament
    -0.09
    osit
    -0.09
    .stride
    -0.09
     arreglo
    -0.09
    Positive Logits
    avis
    0.11
     UIP
    0.10
    awan
    0.10
     flare
    0.09
    334
    0.09
     Hann
    0.09
     Na
    0.09
     pep
    0.09
    yk
    0.09
    yr
    0.09
    /shared
    0.09
    535
    0.09
    yd
    0.09
    _MetaData
    0.09
     hann
    0.09
    ータ
    0.09
    odyn
    0.09
     necessarily
    0.09
     �
    0.09
    263
    0.09
    Activations Density 51.424%
    Loading dashboard...