© 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. 39103
    Prev
    Next
    INDEX
    Explanations

    ultimately, then conclusion

    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
    é¡¿æŶ
    -0.09
    à¸ĵ
    -0.08
    haj
    -0.08
    acho
    -0.07
    jada
    -0.07
    ä¼ĹæīĢåij¨çŁ¥
    -0.07
    åİĨæĿ¥
    -0.07
    ç»ĪæĹ¥
    -0.07
    es
    -0.07
    edly
    -0.07
    POSITIVE LOGITS
    ãģ®ãģ¨ãģĵãĤį
    0.13
    umbo
    0.10
    å½Ĵ宿
    0.09
    æľīä¸Ģ天
    0.09
    è¿ĺæĺ¯è¦ģ
    0.08
    è¦ģéĿł
    0.08
     اÛĮÙĨÚ©Ùĩ
    0.08
    most
    0.08
     конÑĨов
    0.08
    lass
    0.08
    Activations Density 0.037%

    No Known Activations