© 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. Llama3.3-70B-IT
    5. MLP Neurons - Layer 21
    7. 305
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    USTOM
    -0.10
     typedef
    -0.10
     Col
    -0.10
    ric
    -0.10
     packet
    -0.10
     Stark
    -0.10
    packet
    -0.10
    jest
    -0.09
    rico
    -0.09
    斗
    -0.09
     Sark
    -0.09
    的话
    -0.09
     Rico
    -0.09
    鲜
    -0.09
    ifa
    -0.09
    EEK
    -0.09
    |,↵
    -0.09
     Packet
    -0.09
    chter
    -0.09
    _exc
    -0.09
    Positive Logits
     rein
    0.11
    ombat
    0.10
     Rug
    0.10
    isson
    0.10
    ・・・↵↵
    0.10
     Rein
    0.10
    BITS
    0.09
    ｊ
    0.09
     memo
    0.09
    CFG
    0.09
     Diss
    0.09
    cum
    0.09
     inse
    0.09
    inia
    0.09
     Gins
    0.09
    ESIS
    0.09
    SMART
    0.08
    getMethod
    0.08
     spared
    0.08
    xC
    0.08
    Activations Density 51.173%
    Loading dashboard...