© 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. 24236
    Prev
    Next
    INDEX
    Explanations

    innings pitched

    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
    afia
    -0.08
    esia
    -0.07
    è°Ĭ
    -0.07
    åĴĮåĽ¾çīĩ
    -0.07
    è´¨
    -0.07
    rss
    -0.07
    踩
    -0.06
    åķ¸
    -0.06
    erie
    -0.06
     locating
    -0.06
    POSITIVE LOGITS
    èµĦæºIJç½ij
    0.07
    eman
    0.07
    ograd
    0.07
    dling
    0.07
    ä¸Ĭä¼ł
    0.07
    lap
    0.07
    arton
    0.06
    .removeEventListener
    0.06
     emin
    0.06
    /slick
    0.06
    Activations Density 0.093%

    No Known Activations