© 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. 2620
    Prev
    Next
    INDEX
    Explanations

    say "char"

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

    No Comments

    Negative Logits
    emand
    -16.75
    pent
    -16.00
    chod
    -15.19
    antic
    -15.13
     antigen
    -15.06
     pent
    -14.81
     Instruments
    -14.13
    搓
    -13.88
    ereg
    -13.50
    羔
    -13.50
    POSITIVE LOGITS
     char
    94.00
    char
    88.00
     Char
    86.50
    Char
    85.00
    (char
    79.00
    [char
    77.00
    -char
    76.50
    ,char
    75.00
    _char
    73.00
    	char
    72.50
    Activations Density 0.287%

    No Known Activations