© 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. 2960
    Prev
    Next
    INDEX
    Explanations

    say 影

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

    No Comments

    Negative Logits
     Registered
    -19.00
    Registered
    -18.63
    [cur
    -15.88
    .Register
    -15.06
    十里
    -14.69
     civ
    -14.56
    pirit
    -14.56
     derivation
    -14.13
     registered
    -14.00
    僧
    -14.00
    POSITIVE LOGITS
    影像
    53.50
    影
    51.75
    影片
    42.25
     img
    41.75
    	img
    41.00
    =img
    40.00
     film
    39.50
    (img
    39.25
    img
    38.50
    Film
    38.50
    Activations Density 0.048%

    No Known Activations