© 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. 33032
    Prev
    Next
    INDEX
    Explanations

    config, cert, version, or arch

    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
    Appe
    -0.07
    åĴª
    -0.07
    ¶ļ
    -0.07
     verm
    -0.07
    æĸĩåĵ²
    -0.07
    èİ·èµŀ
    -0.07
     ((__
    -0.07
    ä¸įåĪ°äºĨ
    -0.06
    èĮĥåĦ¿
    -0.06
    goo
    -0.06
    POSITIVE LOGITS
    eter
    0.07
     (âĢ¦)
    0.07
    çİĭ家
    0.07
    _configuration
    0.07
    Å«t
    0.07
    è°ĥæŁ¥æĬ¥åijĬ
    0.07
    _draft
    0.06
     embryo
    0.06
    пÑĤи
    0.06
     nguyá»ĩn
    0.06
    Activations Density 0.456%

    No Known Activations