© 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. 25256
    Prev
    Next
    INDEX
    Explanations

    less than ideal

    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
    ÑĪÑĤей
    -0.08
    utenberg
    -0.07
    æĢ»æ¯Ķ
    -0.07
    æ¡IJ
    -0.07
    holm
    -0.07
    ä¸ŃåĽ½åĪ¶éĢł
    -0.07
     Wandel
    -0.07
     lip
    -0.07
     Ùħعد
    -0.07
    èĤ¯
    -0.07
    POSITIVE LOGITS
    ä¸įå¦Ĥ
    0.08
    oba
    0.08
    ä¸į建议
    0.08
     inferior
    0.07
    aca
    0.07
    rost
    0.07
    éĢĬèī²
    0.07
    è¿ĺä¸įå¦Ĥ
    0.07
    éĻ¤éĿŀ
    0.07
    alu
    0.07
    Activations Density 0.044%

    No Known Activations