© 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. 29273
    Prev
    Next
    INDEX
    Explanations

    Ajax requests

    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
    缴æİ¥æĪĸ
    -0.07
    严
    -0.06
    ÙģÙĩ
    -0.06
    çĶ¨ä½ľ
    -0.06
    åİĨ代
    -0.06
    缴æİ¥æĪĸéĹ´æİ¥
    -0.06
    enie
    -0.06
    æĭĻ
    -0.06
    éĹ´æİ¥
    -0.06
    ogh
    -0.06
    POSITIVE LOGITS
    éĴĪ对ä¸įåIJĮ
    0.13
     separately
    0.11
    对ä¸įåIJĮ
    0.10
    åĪĨå¼Ģ
    0.09
    éĴĪ对æĢ§
    0.09
     targeted
    0.09
     differently
    0.09
    满足ä¸įåIJĮ
    0.09
    çļĦä¸įåIJĮ
    0.09
     individually
    0.09
    Activations Density 0.492%

    No Known Activations