© 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. 38961
    Prev
    Next
    INDEX
    Explanations

    .file extensions

    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
    æ´Ĵ水车
    -0.06
     (
    -0.06
    ÑĪне
    -0.06
    åĽŀæĹĭ
    -0.06
    à¸ĺà¹Į
    -0.06
    rame
    -0.06
    èĥ½è§ģ度
    -0.05
     Jr
    -0.05
    2
    -0.05
    inct
    -0.05
    POSITIVE LOGITS
    åħĥ人æ°ijå¸ģ
    0.08
    .${
    0.08
     Seger
    0.08
    untime
    0.08
    -addons
    0.08
    /--
    0.08
    ç½Ĺ纳
    0.08
    =>'
    0.07
    omencl
    0.07
    æĪijçļĦå°ı
    0.07
    Activations Density 0.030%

    No Known Activations