© 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. 21698
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and code snippets

    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
    ahkan
    -0.07
     Miser
    -0.07
    ABLE
    -0.07
    èĤ¢
    -0.07
    æ¡¥åĮº
    -0.06
    Fabr
    -0.06
    踵
    -0.06
    æĭĤ
    -0.06
    chern
    -0.06
     ë§Ŀ
    -0.06
    POSITIVE LOGITS
    微信æī«ä¸Ģæī«
    0.08
    éĥ½ä¸įè¦ģ
    0.07
    åĨĻä¸Ĭ
    0.07
    ÑģаÑĢ
    0.07
    ูà¸Ļ
    0.07
    讲çļĦ
    0.07
    ึà¸ģ
    0.07
     pim
    0.06
    stown
    0.06
    uten
    0.06
    Activations Density 0.002%

    No Known Activations