© 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. 7996
    Prev
    Next
    INDEX
    Explanations

    copyright and license notices

    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
    <|box_end|>
    -0.12
    èĩªå·±
    -0.09
    µ
    -0.09
    yla
    -0.09
    yle
    -0.08
    èĩªå·±æ²¡æľī
    -0.08
    iveau
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    -ever
    -0.08
    hältnis
    -0.08
    POSITIVE LOGITS
    //*
    0.09
    ़
    0.09
    à¥ĩ
    0.08
    ic
    0.08
    Ø©
    0.08
    eel
    0.08
    ação
    0.08
    ing
    0.08
    ej
    0.08
    ت
    0.08
    Activations Density 0.226%

    No Known Activations