© 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. 33308
    Prev
    Next
    INDEX
    Explanations

    bank held, automobile negligence, the privacy

    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
    rego
    -0.08
    åĨĹ
    -0.07
    ê·
    -0.07
    强åģ¥
    -0.07
    建档ç«ĭ
    -0.07
    Exited
    -0.07
    aÅĤ
    -0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯
    -0.07
    _priv
    -0.07
    edizione
    -0.07
    POSITIVE LOGITS
    认å®ļ为
    0.10
    åĩºåħ·çļĦ
    0.08
    认å®ļ
    0.08
    äºīè®®çļĦ
    0.08
    åħ·æľīä¸Ģå®ļ
    0.08
    è¯ģæį®è¯ģæĺİ
    0.08
    åı¸æ³ķ解éĩĬ
    0.08
    æľĢé«ĺ人æ°ijæ³ķéĻ¢
    0.07
    èªįå®ļ
    0.07
    åĸĦæĦı
    0.07
    Activations Density 0.015%

    No Known Activations