© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1378
    Prev
    Next
    INDEX
    Explanations

    [credit] => [credit]

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

    No Comments

    Negative Logits
    信用
    -43.75
     credit
    -38.75
    Credit
    -35.50
     Credit
    -34.50
    _credit
    -29.75
    credit
    -29.13
    Credits
    -27.63
     Credits
    -26.88
     credits
    -26.13
    .credit
    -26.13
    POSITIVE LOGITS
     Lawson
    14.94
     science
    14.81
    anto
    14.63
    法律顾问
    14.19
    lambda
    13.94
    ASM
    13.75
     Snake
    13.69
     Science
    13.69
     GE
    13.63
     Sea
    13.56
    Activations Density 0.064%

    No Known Activations