© 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. 22525
    Prev
    Next
    INDEX
    Explanations

    with or along

    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
    á»Ń
    -0.07
    asten
    -0.07
    adesh
    -0.07
    å°ıç¼ĸ为大家
    -0.07
     ада
    -0.06
    EntryPoint
    -0.06
    çŃĸ
    -0.06
    æĽ¾ç»ıæĺ¯
    -0.06
    ieux
    -0.06
    éĢļè¿ĩåŃ¦ä¹ł
    -0.06
    POSITIVE LOGITS
    ä¸Ģ并
    0.13
    çļĦè¿ĺæľī
    0.11
    ä¸Ģèµ·
    0.11
    ä¸ĢåIJĮ
    0.10
    éļıä¹ĭ
    0.10
    ä¼´éļıçĿĢ
    0.09
    ä¼´éļı
    0.09
    à¹Ħà¸Ľà¸Ķà¹īวย
    0.09
    åIJĮæŃ¥
    0.09
    èĢĮæĿ¥çļĦ
    0.09
    Activations Density 0.292%

    No Known Activations