© 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. 14400
    Prev
    Next
    INDEX
    Explanations

    say capital-letter acronyms

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

    No Comments

    Negative Logits
    w
    -53.50
    W
    -50.75
    -w
    -49.50
     w
    -48.75
     W
    -46.25
    _w
    -44.75
    ｗ
    -41.50
    .w
    -41.25
    ,w
    -40.50
    +w
    -40.00
    POSITIVE LOGITS
     caramel
    13.38
    岘
    12.69
    bounce
    12.63
    حجر
    12.44
    同情
    12.25
    inds
    12.19
    .bp
    11.94
     noop
    11.94
    千伏
    11.88
    anches
    11.81
    Activations Density 1.295%

    No Known Activations