© 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. 22176
    Prev
    Next
    INDEX
    Explanations

    uint types or 第

    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
    æĸ°åĬłåĿ¡
    -0.12
    åĬłæĭ¿å¤§
    -0.12
    俱ä¹IJéĥ¨
    -0.09
    beck
    -0.08
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
    ../
    -0.08
    lega
    -0.08
    ations
    -0.08
    áĥĵáĥĶ
    -0.08
    éĺ¿æĭī伯
    -0.07
    POSITIVE LOGITS
    kannya
    0.09
    次çļĦ
    0.09
    ÙĤÙĬب
    0.09
    à¦ĸানà§ĩ
    0.08
    agonal
    0.08
    OfWeek
    0.08
    æ¯ĶåĪ©
    0.08
    ughters
    0.08
    ãĢħãģ®
    0.08
    gados
    0.08
    Activations Density 0.009%

    No Known Activations