© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8576
    Prev
    Next
    INDEX
    Explanations

    Instagram, Pinterest, Duration, Retrieved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .gnu
    -0.09
    Âł
    -0.08
    宫å¤ĸ
    -0.07
    ä¹Łåĥı
    -0.07
    ³³³³³³³
    -0.07
     Appropri
    -0.07
    ç»Īç»ĵ
    -0.06
    踵
    -0.06
    ³³³³³³³³
    -0.06
    ³³³³
    -0.06
    POSITIVE LOGITS
    _parsed
    0.08
    eshire
    0.08
    ignez
    0.08
    enton
    0.07
    alani
    0.06
    _pars
    0.06
    جز
    0.06
    ritz
    0.06
    _ATTRIB
    0.06
    æĸĩæĺİ礼仪
    0.06
    Activations Density 0.146%

    No Known Activations