© 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. 2848
    Prev
    Next
    INDEX
    Explanations

    say "dem"

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

    No Comments

    Negative Logits
    mino
    -14.69
     Tube
    -14.56
    Mirror
    -14.25
    旋
    -14.06
    modify
    -13.81
    ơ
    -13.69
     Tubes
    -13.69
    -cert
    -13.56
    otto
    -13.56
    .serial
    -13.56
    POSITIVE LOGITS
     dem
    94.00
     Dem
    88.00
    Dem
    87.00
    dem
    85.00
    _dem
    78.50
    -dem
    72.50
     DEM
    70.50
    DEM
    60.50
     дем
    54.75
     demographic
    54.00
    Activations Density 0.136%

    No Known Activations