© 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. 1511
    Prev
    Next
    INDEX
    Explanations

    [ste] => [steamed]

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

    No Comments

    Negative Logits
    STE
    -18.38
    编码
    -15.13
    岸
    -14.56
    鲑
    -14.50
     sang
    -14.50
     STE
    -14.44
    sip
    -14.38
    _ste
    -14.31
    塘
    -13.94
    stein
    -13.81
    POSITIVE LOGITS
     mathematic
    19.63
    公交车
    19.25
    体育
    18.88
     brain
    18.25
    数学
    18.00
    城市的
    18.00
    城市
    17.75
    (console
    17.50
     bus
    17.13
    Brain
    17.00
    Activations Density 0.291%

    No Known Activations