© 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. 2957
    Prev
    Next
    INDEX
    Explanations

    genre

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

    No Comments

    Negative Logits
    verified
    -16.88
    ием
    -15.69
     Pot
    -15.63
    itelist
    -15.44
     atol
    -15.38
    .verify
    -15.31
     Verm
    -14.88
    lem
    -14.81
    observer
    -14.69
    PET
    -14.56
    POSITIVE LOGITS
     genre
    66.00
    (gen
    62.75
     Gen
    62.25
    代
    62.25
     gen
    62.00
    	gen
    61.25
     Genre
    57.75
    gen
    55.25
    -gen
    55.25
    genre
    55.00
    Activations Density 0.049%

    No Known Activations