© 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. 57286
    Prev
    Next
    INDEX
    Explanations

    functional include specifications

    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
    nock
    -0.06
    ç§ijåѦä¸İæĬĢæľ¯
    -0.06
    æĮīä¸ĭ
    -0.06
    åĽłäººèĢĮå¼Ĥ
    -0.06
    ima
    -0.06
    åľ¨æ¯ı个
    -0.06
    ieved
    -0.06
    éĢĨå¢ĥ
    -0.06
    ãĥ¼ãĥł
    -0.06
    s
    -0.06
    POSITIVE LOGITS
    诸å¦Ĥ
    0.11
    åĮħæĭ¬
    0.10
     including
    0.10
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.09
     вклÑİÑĩаÑı
    0.09
     incluyendo
    0.09
    è¿ĺåĮħæĭ¬
    0.09
    ä¹ŁåĮħæĭ¬
    0.09
    åĮħæĭ¬äºĨ
    0.09
     شاÙħÙĦ
    0.08
    Activations Density 0.095%

    No Known Activations