© 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. 14055
    Prev
    Next
    INDEX
    Explanations

    say authority

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

    No Comments

    Negative Logits
    getReference
    -18.50
     refund
    -17.13
     beaches
    -17.00
    平坦
    -15.31
    Cleanup
    -15.31
    .env
    -15.00
    海滩
    -14.75
    .cleaned
    -14.63
    水质
    -14.56
    .reference
    -14.38
    POSITIVE LOGITS
    控制
    33.00
     control
    31.38
    控制系统
    29.75
    authority
    28.88
     Control
    28.50
    control
    28.38
    权力
    28.13
    Control
    27.88
    Authority
    27.50
     authority
    26.75
    Activations Density 1.123%

    No Known Activations