© 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. 14169
    Prev
    Next
    INDEX
    Explanations

    say report words

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

    No Comments

    Negative Logits
    _CHARACTER
    -18.25
     behaviour
    -17.13
    DisplayStyle
    -16.75
    谱
    -16.63
    行为
    -16.25
    Collections
    -16.13
    表现
    -16.00
    .character
    -16.00
     TARGET
    -15.69
    collections
    -15.63
    POSITIVE LOGITS
     reports
    17.75
    /report
    16.88
    Reporting
    16.88
    报告
    16.88
     reporting
    16.25
    省政府
    16.13
    Reports
    16.13
     Reports
    15.94
     report
    15.88
    reports
    15.69
    Activations Density 0.925%

    No Known Activations