© 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. 4253
    Prev
    Next
    INDEX
    Explanations

    percentages and fractions

    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
    ä¹ĺ
    -0.08
    æĹ¥æĸ°æľĪå¼Ĥ
    -0.07
     Mansion
    -0.07
    /html
    -0.07
    wak
    -0.07
    ÑĨеп
    -0.06
    quio
    -0.06
     applied
    -0.06
    endr
    -0.06
    使åij½
    -0.06
    POSITIVE LOGITS
    æĢ»æķ°
    0.12
    æĢ»æķ°çļĦ
    0.10
     counted
    0.10
    人æķ¸
    0.09
    åħ±è®¡
    0.09
     تعداد
    0.09
    æĢ»è®¡
    0.09
    åIJĪè¨Ī
    0.09
    人æķ°
    0.09
     counts
    0.09
    Activations Density 0.110%

    No Known Activations