© 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. 25555
    Prev
    Next
    INDEX
    Explanations

    porn, iphone, sites

    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
    emit
    -0.09
    ä¼¼æĺ¯
    -0.07
    imore
    -0.07
     Parks
    -0.07
    ormais
    -0.06
    estin
    -0.06
    ."\
    -0.06
    paginate
    -0.06
    çĹĽç»ı
    -0.06
    \:
    -0.06
    POSITIVE LOGITS
    çļĦå°ıç¼ĸ
    0.07
    婧
    0.07
    ially
    0.07
    è®ĵæĤ¨
    0.07
    ake
    0.06
    èĴĤæĸ¯
    0.06
    onio
    0.06
     terk
    0.06
    .|
    0.06
    æĿ¥ä¸ºå¤§å®¶
    0.06
    Activations Density 0.179%

    No Known Activations