© 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. 8532
    Prev
    Next
    INDEX
    Explanations

    not exactly / not quite sure

    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
     تÙĤرÙĬب
    -0.08
    ä¹ĭä¸į
    -0.08
     sopr
    -0.08
     competente
    -0.08
    inkel
    -0.08
    ParseException
    -0.08
    **”,
    -0.08
     Gund
    -0.08
    lach
    -0.07
    unci
    -0.07
    POSITIVE LOGITS
    ä½Ĩåı¯ä»¥
    0.09
    ä¸ĢåĽŀäºĭ
    0.08
    ä½Ĩèĩ³å°ij
    0.08
     anymore
    0.07
     sondern
    0.07
    èĢĮæĺ¯
    0.07
    "
    0.06
     lagi
    0.06
    æł·çļĦ
    0.06
    åĽŀäºĭ
    0.06
    Activations Density 0.009%

    No Known Activations