© 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. 2207
    Prev
    Next
    INDEX
    Explanations

    know if

    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
    ÑģÑĤане
    -0.08
    ��
    -0.07
    à¸ĩ
    -0.07
    elik
    -0.07
    PRETTY
    -0.07
    ãģ¨ãĤĤãģ«
    -0.07
     Sut
    -0.06
    å·¥ç¨ĭçŃī
    -0.06
    åĽ½äºº
    -0.06
    俺
    -0.06
    POSITIVE LOGITS
     λοι
    0.08
    çļĦè¿Ļç§į
    0.08
    éĻ¤æѤ
    0.07
    è¿Ļæĸ¹éĿ¢
    0.07
    è¿ĻäºĽ
    0.06
    好
    0.06
    Įĵ
    0.06
    anship
    0.06
     empt
    0.06
     découvrez
    0.06
    Activations Density 0.013%

    No Known Activations