© 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. 30986
    Prev
    Next
    INDEX
    Explanations

    not work

    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
    èģĶ系客æľį
    -0.09
    符åIJĪåĽ½å®¶
    -0.08
    Õ¡Õ£
    -0.08
    æľīå¿Ĺ
    -0.08
    屬æĸ¼
    -0.08
    ÌĢ
    -0.08
    èĦ¸åºŀ
    -0.07
     yourselves
    -0.07
    ä¹Łåı¯ä»¥æĺ¯
    -0.07
     пÑĢинадлежиÑĤ
    -0.07
    POSITIVE LOGITS
    ä¸į误
    0.08
     output
    0.08
    ä¸įæĬĬ
    0.08
     detecting
    0.07
    æįķæįī
    0.07
     detects
    0.07
    åĪĽå§ĭ人
    0.07
    detect
    0.07
    åľ¨å¤ĦçIJĨ
    0.07
    æ¡ĥ
    0.06
    Activations Density 0.091%

    No Known Activations