© 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. 63253
    Prev
    Next
    INDEX
    Explanations

    vs women

    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
    å·¥ç¨ĭçŃī
    -0.08
    esson
    -0.08
    andia
    -0.08
    缸åħ³äºĭå®ľ
    -0.07
    æľįåĬ¡çŃī
    -0.07
    озÑıй
    -0.07
    валиÑĦиÑĨи
    -0.07
    è¿ĺæĺ¯ä¸Ģ个
    -0.07
    inna
    -0.07
    achim
    -0.07
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.07
     eds
    0.07
    evin
    0.07
    <|box_end|>
    0.06
    ftype
    0.06
    ãĤ£
    0.06
    ¬
    0.06
    ebb
    0.06
    éĻĨ
    0.06
    olak
    0.06
    Activations Density 0.091%

    No Known Activations