© 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. 2154
    Prev
    Next
    INDEX
    Explanations

    say cal

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

    No Comments

    Negative Logits
    杵
    -16.25
    透
    -16.13
    permissions
    -16.13
    师父
    -15.56
     Pert
    -15.44
    .permissions
    -14.94
    掌
    -14.50
     onKeyDown
    -14.31
     �
    -14.25
     pert
    -13.94
    POSITIVE LOGITS
     cal
    93.00
     Cal
    89.00
    Cal
    87.00
    cal
    80.00
    (cal
    79.50
    	cal
    79.50
    -cal
    71.00
    .cal
    69.50
     calibration
    69.00
    /cal
    66.50
    Activations Density 0.258%

    No Known Activations