© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15132
    Prev
    Next
    INDEX
    Explanations

    author surnames

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

    No Comments

    Negative Logits
    of
    -17.75
    oz
    -13.81
    ói
    -13.63
    gether
    -12.94
    /
    -12.88
    oo
    -12.06
    问题
    -12.00
    次
    -11.81
    zie
    -11.56
    +
    -11.50
    POSITIVE LOGITS
    lav
    16.88
     средне
    16.88
    之势
    16.88
    鞍
    16.75
    后悔
    16.63
    inear
    16.50
    手势
    16.50
    alin
    16.50
    uran
    16.38
    grand
    16.38
    Activations Density 0.052%

    No Known Activations