© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14074
    Prev
    Next
    INDEX
    Explanations

    gamma, alpha, beta

    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
    çļĦ为
    -0.07
    å¿ĺåį´
    -0.07
    è°ģçļĦ
    -0.07
    aggable
    -0.07
    intang
    -0.07
    ستاÙĨÛĮ
    -0.07
    åIJĪåIJĮæŶ
    -0.07
    /of
    -0.06
    abbage
    -0.06
    bpp
    -0.06
    POSITIVE LOGITS
    ä¹Łç½¢
    0.12
    çłĶ究表æĺİ
    0.09
    èĢĮè¨Ģä¹ĭ
    0.08
     étant
    0.08
    çĶ¨æĪ·åı¯ä»¥
    0.07
    çĶ¨æĪ·åı¯ä»¥éĢļè¿ĩ
    0.07
    åѦåijĺ们
    0.07
    åħ¬åı¸æĭ¥æľī
    0.07
     ê·¸ëłĩ
    0.07
     íķľíݸ
    0.07
    Activations Density 1.048%

    No Known Activations