© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14366
    Prev
    Next
    INDEX
    Explanations

    [=] => [number]

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

    No Comments

    Negative Logits
    WARE
    -20.50
    [player
    -18.63
     Stard
    -17.88
    [res
    -17.50
    spl
    -17.50
    WAR
    -17.00
    touches
    -17.00
    ially
    -17.00
    aylight
    -17.00
    liga
    -16.63
    POSITIVE LOGITS
    ok
    17.38
    oke
    15.75
    OME
    13.31
    um
    13.31
    otion
    13.00
    ogi
    13.00
    .restore
    12.75
    ốt
    12.63
     inverse
    12.31
    atrix
    12.25
    Activations Density 0.019%

    No Known Activations