© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13998
    Prev
    Next
    INDEX
    Explanations

    explaining or guessing assumptions

    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
    æĺĬ天
    -0.08
    éĿ¡
    -0.08
    ulumi
    -0.08
    หว
    -0.08
    atk
    -0.07
    atform
    -0.07
    ä½Ĩå®ŀéĻħä¸Ĭ
    -0.07
    llx
    -0.07
    xE
    -0.07
     peacefully
    -0.07
    POSITIVE LOGITS
     general
    0.08
    ä¸ĢèĪ¬èĢĮè¨Ģ
    0.08
     generally
    0.07
     assumes
    0.07
    æĻ®éģį
    0.07
    ä¸ĢèĪ¬çļĦãģª
    0.07
     typical
    0.07
     ìĿ¼ë°ĺìłģìĿ¸
    0.07
    oo
    0.07
     assume
    0.07
    Activations Density 0.031%

    No Known Activations