© 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. 33737
    Prev
    Next
    INDEX
    Explanations

    latex and programming code snippets

    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
    uhe
    -0.07
    upe
    -0.07
    fft
    -0.07
     Caff
    -0.07
    docs
    -0.07
    rave
    -0.07
    _frm
    -0.07
    ÑĢази
    -0.07
    owie
    -0.06
    顾
    -0.06
    POSITIVE LOGITS
     Unic
    0.08
    æ§ĥ
    0.07
    æīĢæıIJä¾ĽçļĦ
    0.07
    æĺ¯åIJĮ
    0.07
    ADR
    0.07
    ãģįãģª
    0.07
    irm
    0.07
     gern
    0.06
    伶ä¿IJ
    0.06
    <|box_end|>
    0.06
    Activations Density 0.002%

    No Known Activations