© 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. 2113
    Prev
    Next
    INDEX
    Explanations

    arg

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

    No Comments

    Negative Logits
    .pet
    -18.75
    PET
    -18.75
    eten
    -18.13
    _pet
    -16.63
    ET
    -16.50
    tem
    -16.25
    et
    -16.25
     pets
    -16.00
    .modal
    -15.81
     liberties
    -15.81
    POSITIVE LOGITS
     arg
    70.50
    arg
    62.75
    	arg
    62.50
     Arg
    62.25
    Arg
    60.00
    (arg
    59.25
    .arg
    57.50
    [arg
    53.75
    ,arg
    52.75
    _arg
    50.75
    Activations Density 0.123%

    No Known Activations