© 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. 8469
    Prev
    Next
    INDEX
    Explanations

    comparison, count, or proportion

    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
    ×ij×Ķ
    -0.06
    echt
    -0.06
    à¹Īà¸Ļ
    -0.06
    说åIJ§
    -0.06
    orra
    -0.06
    ÑģÑĮ
    -0.05
    erland
    -0.05
    kl
    -0.05
    å»ºåĽ½
    -0.05
    è®°
    -0.05
    POSITIVE LOGITS
    /WebAPI
    0.07
    请ä¸ĭè½½
    0.07
     ATTRIBUTE
    0.07
    îtr
    0.07
    å°ĶèĴĻ
    0.07
    åıĮèĸª
    0.07
    èĭ¦è¾£
    0.07
    ingend
    0.07
    æĸĩåĵ²
    0.07
    ä¸įåı¯åıĬ
    0.07
    Activations Density 0.057%

    No Known Activations