© 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. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15023
    Prev
    Next
    INDEX
    Explanations

    archaeology

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idl
    -17.75
    edBy
    -17.38
    idUser
    -16.00
    enums
    -15.81
    auen
    -15.75
    uant
    -15.56
    asticsearch
    -15.56
     владельц
    -15.44
    ň
    -15.38
    Ident
    -15.31
    POSITIVE LOGITS
    weis
    14.94
     licens
    14.06
    文体
    13.81
    罪
    13.50
     Hint
    13.38
     Americas
    13.19
    .lib
    12.94
    NCY
    12.81
    揍
    12.63
     "+↵
    12.56
    Activations Density 0.187%

    No Known Activations