© 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. 55374
    Prev
    Next
    INDEX
    Explanations

    scientific notation and large numbers

    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
    æıĸ
    -0.09
    éŨå¸Ĥ
    -0.08
    ovel
    -0.07
    éĵ²
    -0.07
    etje
    -0.06
    /ay
    -0.06
     uninsured
    -0.06
    icité
    -0.06
     proced
    -0.06
    ä½ľçĶ¨çļĦ
    -0.06
    POSITIVE LOGITS
    dra
    0.08
    дÑĮми
    0.07
    lias
    0.07
    ndo
    0.07
    ähr
    0.07
    phe
    0.07
    pth
    0.07
    æĿ¥åIJ§
    0.07
    tte
    0.07
     kte
    0.07
    Activations Density 0.004%

    No Known Activations