© 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. 15423
    Prev
    Next
    INDEX
    Explanations

    [奠] => [定]

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

    No Comments

    Negative Logits
    ancellor
    -15.19
    orman
    -14.88
     Curso
    -14.75
    逆转
    -14.75
    .getColumn
    -14.75
    Curso
    -14.56
    și
    -14.50
     euler
    -14.19
    NetMessage
    -13.88
    	anim
    -13.81
    POSITIVE LOGITS
    提供
    22.00
    用户提供
    21.00
    Provid
    20.75
    提供更多
    20.63
    提供的
    19.13
    provide
    18.88
     providing
    18.63
     Providing
    18.50
     provided
    18.25
     provider
    17.50
    Activations Density 0.165%

    No Known Activations