© 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. 2584
    Prev
    Next
    INDEX
    Explanations

    say "lib"

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

    No Comments

    Negative Logits
     det
    -20.50
    (det
    -18.25
    det
    -18.13
     doc
    -17.00
     Det
    -16.63
    -det
    -15.63
    DET
    -15.50
    Det
    -15.44
    .det
    -14.94
     Expr
    -14.88
    POSITIVE LOGITS
    	lib
    64.50
     lib
    62.50
    (lib
    62.25
    lib
    61.75
    Lib
    61.00
     Lib
    56.75
     liberal
    54.75
     LIB
    54.75
     Liberal
    54.50
    -lib
    54.00
    Activations Density 0.086%

    No Known Activations