© 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. 9921
    Prev
    Next
    INDEX
    Explanations

    technical subjects and acronyms

    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
    enhagen
    -0.08
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    enho
    -0.07
    ÑıÑĤи
    -0.06
    æ¯ĶæĻ®éĢļ
    -0.06
    å°Ĩè¿Ļ
    -0.06
    缮ä¸Ń
    -0.06
    å°Ĩ该
    -0.06
     Dout
    -0.06
    äºĨæĮĩ
    -0.06
    POSITIVE LOGITS
    åıĬåħ¶åºĶçĶ¨
    0.11
    产åĵģåıĬ
    0.09
    ÏİÏĤ
    0.08
    è¿ĩç¨ĭåĴĮ
    0.08
    åŁºç¡ĢåĴĮ
    0.08
    åĽĽæĺŁ
    0.08
    åıĬåºĶçĶ¨
    0.08
    SENT
    0.07
    สà¸ĩ
    0.07
    åıĬåħ¶
    0.07
    Activations Density 0.016%

    No Known Activations