© 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. 430
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    rip
    -0.11
     defe
    -0.11
    ilib
    -0.10
    mare
    -0.10
    /part
    -0.10
    -paced
    -0.10
    cord
    -0.10
    geh
    -0.09
     Pod
    -0.09
    ences
    -0.09
    邦
    -0.09
    /big
    -0.09
     Hogwarts
    -0.09
     Luz
    -0.09
     Flux
    -0.09
    .community
    -0.09
     SPL
    -0.09
    歲
    -0.09
     Closing
    -0.09
    /problem
    -0.09
    Positive Logits
    peria
    0.12
    alsy
    0.12
     spike
    0.10
    USAGE
    0.10
    printStats
    0.10
    闲
    0.10
     Loft
    0.10
    ihanna
    0.09
    agger
    0.09
    maktan
    0.09
    amma
    0.09
    řeba
    0.09
     Beats
    0.09
    ombok
    0.09
     uplat
    0.09
    薄
    0.09
    oulder
    0.09
    　　 　 　 　
    0.09
     Pant
    0.09
     :.
    0.09
    Activations Density 52.094%
    Loading dashboard...