© 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. 2327
    Prev
    Next
    INDEX
    Explanations

    say pen

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

    No Comments

    Negative Logits
    arness
    -15.56
    kat
    -15.31
    htag
    -15.00
    有色
    -14.69
     Cond
    -14.56
    stile
    -14.00
     configs
    -13.94
    慝
    -13.88
    Lat
    -13.88
    Cond
    -13.69
    POSITIVE LOGITS
    笔
    93.50
     pen
    83.50
    筆
    80.00
    Pen
    75.50
     Pen
    75.50
    pen
    69.50
    _pen
    67.50
     PEN
    56.25
    .pen
    55.00
     pens
    48.00
    Activations Density 0.091%

    No Known Activations