© 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. 2401
    Prev
    Next
    INDEX
    Explanations

    gen

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

    No Comments

    Negative Logits
    グ
    -16.13
    gree
    -15.63
    gard
    -14.88
    Metric
    -14.13
    istical
    -13.94
    冕
    -13.75
    效益
    -13.75
    HTTPHeader
    -13.63
    DER
    -13.56
    ám
    -13.56
    POSITIVE LOGITS
     gen
    102.00
     Gen
    99.00
    (gen
    93.00
    Gen
    90.50
    gen
    89.50
    	gen
    84.50
    -gen
    84.00
    _gen
    82.00
    .gen
    81.00
     GEN
    80.50
    Activations Density 0.254%

    No Known Activations