© 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. 13410
    Prev
    Next
    INDEX
    Explanations

    lacks or insufficient

    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
    ä¹Łæĺ¯åı¯ä»¥
    -0.08
    ä¸įä¼ļå½±åĵį
    -0.08
    ä¸įéľĢ
    -0.08
    ä¸įåı¯èĥ½çļĦ
    -0.07
     wherever
    -0.07
    毫æĹłçĸijéĹ®
    -0.07
    æĹłå®³
    -0.07
    åĪĨå¤ĸ
    -0.07
    ä¸įè¨ĢèĢĮåĸ»
    -0.06
    ä¸įæĢķ
    -0.06
    POSITIVE LOGITS
     insufficient
    0.16
     недоÑģÑĤаÑĤоÑĩно
    0.16
    缺å°ij
    0.15
    ä¸įå¤Ł
    0.15
    缺ä¹ı
    0.15
     inadequate
    0.13
     lacks
    0.13
     lacked
    0.13
    太å°ij
    0.13
    没èĥ½
    0.12
    Activations Density 0.340%

    No Known Activations