© 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. 13750
    Prev
    Next
    INDEX
    Explanations

    recording medium, database, message

    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
    undas
    -0.08
    Ú¯ÛĮ
    -0.07
    躺çĿĢ
    -0.07
    /trans
    -0.07
    _TRANS
    -0.07
    ë¡Ŀ
    -0.07
    ç»ıæµİè´¸æĺĵ
    -0.07
    ffa
    -0.07
    Ĥ¬
    -0.07
    afi
    -0.07
    POSITIVE LOGITS
    ä¸Ĭ空
    0.07
     Temb
    0.07
    rics
    0.07
    коммÑĥ
    0.07
    èĪªç©º
    0.07
    compound
    0.06
     shar
    0.06
    iraz
    0.06
    ABCDEFGHI
    0.06
    æľºç¼ĺ
    0.06
    Activations Density 0.033%

    No Known Activations