© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62787
    Prev
    Next
    INDEX
    Explanations

    conclusion, change, blame

    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
    éĹ¹
    -0.08
    utely
    -0.08
    åıªä¼ļ
    -0.08
    ç»Ŀ对ä¸įæĺ¯
    -0.07
    è¿ĺæľī许å¤ļ
    -0.07
    xis
    -0.07
    ousel
    -0.07
    ÑĥпиÑĤÑĮ
    -0.07
    ×ķ׳
    -0.07
    ials
    -0.07
    POSITIVE LOGITS
    éĹ´æİ¥
    0.09
     indirect
    0.08
     indirectly
    0.08
     indire
    0.07
    天ä»Ļ
    0.07
     gián
    0.07
    ç¡®å®ŀ
    0.07
    ç´§å¯Ĩ
    0.07
    éĻ¤å¤ĸ
    0.06
    æĬ½åĩº
    0.06
    Activations Density 0.086%

    No Known Activations