© 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. 38051
    Prev
    Next
    INDEX
    Explanations

    article links and publications

    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
    -0.08
    è¯ģåĪ¸äº¤æĺĵæīĢ
    -0.07
    çļĦä»»ä½ķ
    -0.07
    ****
    -0.07
    HttpServletRequest
    -0.07
    aka
    -0.06
    个人页
    -0.06
    ä»»ä½ķä¸Ģç§į
    -0.06
     Evel
    -0.06
     wanting
    -0.06
    POSITIVE LOGITS
    beda
    0.08
    elts
    0.07
    æľīèī²
    0.07
    óf
    0.07
    ford
    0.07
     numbered
    0.07
    illez
    0.07
    iffs
    0.07
    ç»ıæµİåѦéĻ¢
    0.07
    estre
    0.07
    Activations Density 0.005%

    No Known Activations