© 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. 23636
    Prev
    Next
    INDEX
    Explanations

    legal document metadata

    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
    cess
    -0.07
    itom
    -0.07
     cô
    -0.06
    angi
    -0.06
    çĽijå§Ķ
    -0.06
    æĹłä¸Ģ
    -0.06
     Fundação
    -0.06
    eter
    -0.06
    ]int
    -0.06
    ?>>
    -0.06
    POSITIVE LOGITS
    ä¸Ģä¹Ŀ
    0.08
    人åijĺåIJįåįķ
    0.08
    令åĴĮ
    0.07
     dated
    0.07
    ÙĢÙĢÙĢÙĢÙĢÙĢÙĢÙĢ
    0.07
    æļĤè¡Į
    0.07
    ç»´ä¿®æľįåĬ¡
    0.07
    æĿ¥åķ¦
    0.07
    opal
    0.07
    rohr
    0.07
    Activations Density 1.186%

    No Known Activations