© 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. 63562
    Prev
    Next
    INDEX
    Explanations

    getPath or label

    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
    åģļåĩºæĿ¥çļĦ
    -0.08
    thon
    -0.08
    andard
    -0.07
    羽翼
    -0.07
    端åĢª
    -0.07
    çĪĽ
    -0.07
     adel
    -0.07
    iser
    -0.07
    æľ¬æĬ¥
    -0.07
    ĵĴ
    -0.07
    POSITIVE LOGITS
    unker
    0.07
    墨
    0.07
    ä¸Ģè¨Ģ
    0.06
     ëĭ¬
    0.06
    apsible
    0.06
     coated
    0.06
    LEV
    0.06
    åĽº
    0.06
    墨水
    0.06
     Levin
    0.06
    Activations Density 0.001%

    No Known Activations