© 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. 9301
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    é»Ħæ²Ļ
    -0.07
    à¸Ĺุà¸Ļ
    -0.07
    äºĮæľ¬
    -0.07
    JOB
    -0.07
    uffy
    -0.07
    elt
    -0.07
    âĺħâĺĨ
    -0.07
    perator
    -0.06
    æĺ¥èĬ±
    -0.06
    æŃ£å¸¸æĥħåĨµä¸ĭ
    -0.06
    POSITIVE LOGITS
    edly
    0.10
    ï¸İ
    0.08
    åª
    0.08
    osu
    0.07
    æľīçļĦæĺ¯
    0.07
    dra
    0.07
    <|box_end|>
    0.07
    icularly
    0.06
    ·
    0.06
    дÑĮ
    0.06
    Activations Density 0.000%

    No Known Activations