© 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. 39277
    Prev
    Next
    INDEX
    Explanations

    porn.com

    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
    é£ĺé£ĺ
    -0.07
    å¼ĢæĶ¾çļĦ
    -0.07
    hait
    -0.07
    arro
    -0.07
    .ndim
    -0.07
    hof
    -0.07
    èĬĴ
    -0.06
     Emergen
    -0.06
    .indent
    -0.06
    æģ¢
    -0.06
    POSITIVE LOGITS
    azon
    0.07
    agnost
    0.07
    ׼
    0.07
    æĪIJçīĩ
    0.07
    eland
    0.06
    umé
    0.06
    amme
    0.06
    è¨Ģ论
    0.06
    ç»Ŀèī²
    0.06
    èĩ´çĶµ
    0.06
    Activations Density 0.243%

    No Known Activations