© 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. 2249
    Prev
    Next
    INDEX
    Explanations

    [元] => [元]

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

    No Comments

    Negative Logits
     prop
    -18.50
    atu
    -17.88
    Den
    -17.00
     perc
    -15.94
    [prop
    -15.50
    ulares
    -15.44
     Den
    -15.31
    [pos
    -15.19
    (prop
    -14.94
    prop
    -14.75
    POSITIVE LOGITS
    元
    87.00
     Met
    57.50
    Met
    54.25
    met
    53.00
     meta
    52.50
     met
    51.75
    (meta
    49.75
     Meta
    49.00
    _met
    49.00
    meta
    48.50
    Activations Density 0.136%

    No Known Activations