© 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. 38463
    Prev
    Next
    INDEX
    Explanations

    DO NOT MODIFY or ALTER

    np_acts-logits-general · gemini-2.5-flash-lite

    warning or notice statements emphasizing important information, typically in all caps (like "DO NOT MODIFY", "IMPORTANT", "EXPERIMENTAL").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
     Ú©ÙħÛĮ
    -0.09
    è¿ĺç®Ĺ
    -0.09
    usk
    -0.09
    åijĹ
    -0.09
    ä¹Łä¸įéĶĻ
    -0.08
    ä¹Łä¸į太
    -0.08
    ä¹ŁæľīäºĽ
    -0.08
    åĢĴä¹Ł
    -0.08
    æĽ´æĸ°æĹ¥æľŁ
    -0.08
    ä¹ŁæĮº
    -0.08
    POSITIVE LOGITS
    !!!
    0.19
    ï¼ģï¼ģï¼ģ
    0.18
    ï¼ģï¼ģ
    0.17
    !!
    0.16
    ï¼ģ
    0.16
    !!!!
    0.15
     !!!
    0.15
    !
    0.15
    !!!!!
    0.14
    !!!!!!!!
    0.14
    Activations Density 0.203%

    No Known Activations