© 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. 62314
    Prev
    Next
    INDEX
    Explanations

    php and html tags

    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
    haft
    -0.08
    addon
    -0.07
    _MALLOC
    -0.07
    å¿ĥçĶĺ
    -0.07
    ation
    -0.06
    edale
    -0.06
    æĻĹ
    -0.06
    天æĢ§
    -0.06
    ulty
    -0.06
    æģº
    -0.06
    POSITIVE LOGITS
    ç±
    0.08
    æĸ°éĹ»èµĦ讯
    0.07
    entif
    0.07
    ìł¸
    0.07
    uce
    0.07
    åŃIJåĴĮ
    0.07
    áh
    0.07
    ifiers
    0.07
    åݿ人æ°ijæĶ¿åºľ
    0.07
    à¹Ģà¸Ľà¸¥à¹Īา
    0.07
    Activations Density 0.005%

    No Known Activations