© 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. 31492
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    ä¸ĭåIJĮ
    -0.09
    {@
    -0.09
     sourceMappingURL
    -0.07
     tratti
    -0.07
    gaste
    -0.07
     käyttää
    -0.07
    youtu
    -0.07
     {@
    -0.07
    ocken
    -0.07
    aurant
    -0.07
    POSITIVE LOGITS
    ÑģÑĮ
    0.07
    йд
    0.07
    loch
    0.06
    ä¸ĢåĪĩçļĦ
    0.06
    åħĨ
    0.06
    ridor
    0.06
    ãģ¾ãģļ
    0.06
    combe
    0.06
    é¦ĸåħĪ
    0.06
    ä¸Ģ
    0.06
    Activations Density 0.172%

    No Known Activations