© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14046
    Prev
    Next
    INDEX
    Explanations

    say category

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

    No Comments

    Negative Logits
     report
    -26.25
    报告
    -26.13
    -report
    -25.63
     Report
    -25.25
    	report
    -24.25
     reporting
    -23.75
     Reporting
    -23.75
    report
    -23.75
    Report
    -23.38
    报
    -22.88
    POSITIVE LOGITS
     解
    17.25
    解
    17.25
     категории
    15.50
    rov
    14.88
    .parser
    14.56
    сен
    14.50
    ategoria
    14.19
    (category
    14.19
     category
    14.06
    endregion
    14.00
    Activations Density 1.162%

    No Known Activations