© 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. 34304
    Prev
    Next
    INDEX
    Explanations

    names followed by says or said

    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
    使å®ĥ
    -0.08
    ில
    -0.08
     شع
    -0.08
    åİĨ代
    -0.07
    ķĮ
    -0.07
     Afinal
    -0.07
    ä¸Ĭ马
    -0.07
    çļĦå¼Ģå§ĭ
    -0.07
    etrie
    -0.07
    alars
    -0.07
    POSITIVE LOGITS
     himself
    0.10
     رØŃÙħÙĩ
    0.09
    æıIJåĩºçļĦ
    0.09
    è§ĤçĤ¹
    0.09
    ç¬Ķä¸ĭçļĦ
    0.08
    æıIJåĩº
    0.08
    opoulos
    0.07
    åįļ士
    0.07
    认为
    0.07
    åħ³äºİ
    0.07
    Activations Density 0.109%

    No Known Activations