© 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. 47121
    Prev
    Next
    INDEX
    Explanations

    appointment at

    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
    iews
    -0.08
    chon
    -0.08
    以ä¸ĭåĩł
    -0.08
    ä¸Ńçݯ
    -0.08
    igna
    -0.07
    /*================================================================
    -0.07
    ìĸ´ëĤĺ
    -0.07
    ilson
    -0.07
    own
    -0.07
    egram
    -0.07
    POSITIVE LOGITS
    è¿Ļ两个
    0.11
    è¿Ļ两
    0.11
    ãģ©ãģ¡ãĤīãĤĤ
    0.10
    è¿Ļ两ç§į
    0.10
     beide
    0.10
     keduanya
    0.09
     entrambi
    0.09
    éĢĻåħ©åĢĭ
    0.09
     entrambe
    0.08
    ãģ©ãģ¡ãĤī
    0.08
    Activations Density 0.100%

    No Known Activations