© 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. 17312
    Prev
    Next
    INDEX
    Explanations

    first element, index, ordinal

    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
    inari
    -0.09
     gär
    -0.08
    éĢĥåĩº
    -0.08
    oggio
    -0.07
     enctype
    -0.07
    oÅĽci
    -0.07
    öss
    -0.07
    rados
    -0.07
    iry
    -0.07
    .NewRequest
    -0.07
    POSITIVE LOGITS
     etc
    0.09
    åĴĮæľĢ
    0.08
    etc
    0.08
     ìĭľìŀijìľ¼ë¡ľ
    0.08
    对åºĶ
    0.08
     corresponds
    0.08
    第ä¸Ģ个
    0.08
    第ä¸Ģä½į
    0.07
     closest
    0.07
    éģ¥éģ¥
    0.07
    Activations Density 0.027%

    No Known Activations