© 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. 14161
    Prev
    Next
    INDEX
    Explanations

    say format

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

    No Comments

    Negative Logits
    维权
    -19.38
    -auth
    -18.88
     authService
    -18.75
    .getPort
    -18.63
     auth
    -18.50
    dealloc
    -18.38
    .auth
    -18.13
    	auth
    -18.00
    AUTH
    -17.88
     AUTH
    -17.63
    POSITIVE LOGITS
    产出
    17.75
    格式
    16.88
    Format
    16.00
     format
    15.94
     output
    15.81
    еств
    15.75
    éc
    15.50
     describing
    15.31
    Outputs
    15.25
    ระบ
    15.13
    Activations Density 0.405%

    No Known Activations