© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49986
    Prev
    Next
    INDEX
    Explanations

    resolved, expand, definition

    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
    人家çļĦ
    -0.08
    ä»İ鼶
    -0.07
    etar
    -0.07
    ãĤ¤ãĥĦ
    -0.07
    comma
    -0.07
    æij¸ç´¢
    -0.07
    çľ¼è§Ĵ
    -0.07
    以满足
    -0.07
    esar
    -0.06
     thôi
    -0.06
    POSITIVE LOGITS
    æĭĨ
    0.09
    åĮĸ
    0.09
    转转
    0.09
    åĮĸ为
    0.08
    æĭĨåĪĨ
    0.08
    åĮĸ解
    0.08
    æĭĨ解
    0.08
    转
    0.08
    æĭĨå¼Ģ
    0.08
     ÑĢаÑģкÑĢÑĭ
    0.08
    Activations Density 0.050%

    No Known Activations