© 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. 12282
    Prev
    Next
    INDEX
    Explanations

    me traiga

    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
    mente
    -0.08
    ly
    -0.08
    ÑģлÑĮ
    -0.08
    æĽ´å¹¿
    -0.07
    idad
    -0.07
    ön
    -0.07
    ÑģÑĮ
    -0.07
    ìļĶ
    -0.07
    à§ĩ
    -0.07
    nellement
    -0.06
    POSITIVE LOGITS
    çļĦå°±æĺ¯
    0.09
    ä¹ĭåıĪ
    0.08
    åĩĨå¤ĩ好äºĨåIJĹ
    0.08
    à¹Ī
    0.07
    åĿĢ
    0.07
    /she
    0.07
    å¾Ĺå¤ļ
    0.07
    åıĬ家éķ¿
    0.07
    hud
    0.07
    Ùİاء
    0.07
    Activations Density 0.023%

    No Known Activations