© 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. 60969
    Prev
    Next
    INDEX
    Explanations

    symptomatic conditions and progression

    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
    issi
    -0.08
    {}.
    -0.07
    unno
    -0.07
    stof
    -0.07
    adou
    -0.07
     Aller
    -0.07
     licenci
    -0.07
    _FD
    -0.07
    ifar
    -0.07
    æľĢä¼Łå¤§çļĦ
    -0.07
    POSITIVE LOGITS
     persistent
    0.09
     imminent
    0.09
     suspected
    0.09
    åıįå¤į
    0.08
    persistent
    0.08
    æĺİæĺ¾
    0.08
    é¡½åĽº
    0.08
    æĪĸèĢħæľī
    0.08
    严éĩįå½±åĵį
    0.08
    ä¸Ķæľī
    0.08
    Activations Density 0.380%

    No Known Activations