© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1577
    Prev
    Next
    INDEX
    Explanations

    context => 资金

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

    No Comments

    Negative Logits
     fire
    -22.13
    -fire
    -21.75
     fires
    -20.50
    fires
    -20.50
     Fire
    -20.50
    fire
    -20.13
    Firestore
    -19.63
    	fire
    -19.63
     firearm
    -19.00
    FS
    -18.75
    POSITIVE LOGITS
    微笑
    19.13
    _html
    17.13
    -html
    16.88
     HTML
    16.75
    HTML
    16.50
    html
    16.50
    海尔
    16.38
     alpha
    16.25
    alpha
    16.13
     html
    15.81
    Activations Density 0.042%

    No Known Activations