© 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. 14560
    Prev
    Next
    INDEX
    Explanations

    say "gram"

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

    No Comments

    Negative Logits
    orde
    -16.13
    过关
    -16.00
    wagon
    -14.94
    BED
    -14.69
    .GetInstance
    -14.56
     GameState
    -14.38
    钫
    -14.38
    GetInstance
    -14.06
    /////////////////////////////////////////////////////////////////////////////↵
    -14.00
    estatus
    -14.00
    POSITIVE LOGITS
    l
    15.63
    heet
    15.31
    Layer
    14.94
    层
    14.94
     parse
    14.94
    lash
    14.81
    layer
    14.63
    parse
    14.31
    parser
    14.25
     Parse
    14.13
    Activations Density 0.024%

    No Known Activations