© 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. 56031
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    à¸Ń
    -0.08
    çī©ãģ¯
    -0.07
    ого
    -0.06
    à¸Ńà¸ģà¸Īาà¸ģ
    -0.06
     "
    -0.06
    åı¯æĺ¯ä»ĸ
    -0.06
    оÑĩно
    -0.06
    udara
    -0.06
    ëĿ½
    -0.06
     **
    -0.06
    POSITIVE LOGITS
     the
    0.13
    çļĦ人æ°Ķ
    0.12
    ’s
    0.11
    çļĦ人åı£
    0.11
    the
    0.11
    _the
    0.11
    çļĦ人åĬĽ
    0.11
    ìĿĺ
    0.10
    çļĦä¸Ģ线
    0.10
    æĹ³
    0.10
    Activations Density 1.047%

    No Known Activations