© 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. 29408
    Prev
    Next
    INDEX
    Explanations

    legal respondents

    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
    ä¼´
    -0.07
    åIJģ
    -0.07
    atur
    -0.07
    åĴĮå®ĮåĸĦ
    -0.06
    ãģ¤ãģį
    -0.06
    ernet
    -0.06
    çĻ¾åĢį
    -0.06
    ục
    -0.06
    éħįå¥Ĺ
    -0.06
    ier
    -0.06
    POSITIVE LOGITS
    éĢ£ç·ļ
    0.09
    ehme
    0.08
    íĥĿ
    0.08
    åħ¬åı¸ä»ĭç»į
    0.08
    usah
    0.08
    åIJĮæµİ
    0.08
    tingham
    0.07
    -Sah
    0.07
    elize
    0.07
    ×ķ×¢
    0.07
    Activations Density 0.003%

    No Known Activations