© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1460
    Prev
    Next
    INDEX
    Explanations

    say film

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

    No Comments

    Negative Logits
     Acc
    -47.50
    Accuracy
    -43.25
     accuracy
    -42.75
     Accuracy
    -42.50
    酸
    -42.25
     accurate
    -39.75
    accuracy
    -39.75
    准确
    -38.75
    Acc
    -38.50
    accur
    -38.50
    POSITIVE LOGITS
    film
    19.75
     film
    18.63
    filme
    17.13
    金华
    16.75
    movie
    16.63
    rod
    16.25
    movies
    16.25
     Film
    16.25
     Worm
    15.31
    ione
    15.06
    Activations Density 0.112%

    No Known Activations