© 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. 13276
    Prev
    Next
    INDEX
    Explanations

    page or line numbers

    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
    olak
    -0.07
    èĢģåİ»
    -0.07
    ä¸ĩéĩĮ
    -0.07
    ocr
    -0.07
    ol
    -0.07
    olik
    -0.07
    éĶĦ
    -0.06
    еÑĩÑĮ
    -0.06
    olarity
    -0.06
    åĨįä¹Łä¸į
    -0.06
    POSITIVE LOGITS
     Glover
    0.07
    ä¹ĭ交
    0.07
    illard
    0.07
    èĬĤçļĦ
    0.07
    èħĮ
    0.07
    tid
    0.07
    è¿ŀç»ŃçļĦ
    0.06
     걸ì³IJ
    0.06
    æķ´ä¸ª
    0.06
    ffe
    0.06
    Activations Density 0.072%

    No Known Activations