© 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. 2433
    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
    乙
    -25.25
    ardin
    -17.75
    这条
    -17.63
    伦理
    -17.13
    _eth
    -17.13
    пло
    -17.00
    (et
    -16.63
    .eth
    -16.63
     des
    -16.50
    simulate
    -16.38
    POSITIVE LOGITS
     PEN
    48.50
     Penn
    48.25
    笔
    48.00
     pen
    47.25
     Pen
    46.50
    Pen
    46.00
    Penn
    42.50
    _pen
    40.50
     Penny
    39.75
    ペン
    39.50
    Activations Density 0.028%

    No Known Activations