© 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. 25253
    Prev
    Next
    INDEX
    Explanations

    trademarks and copyrights

    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
    æĿĤ
    -0.08
    ->[
    -0.07
    ாவ
    -0.07
    è¾
    -0.07
    æ»ŀ
    -0.07
    kompl
    -0.07
    å°ijåħĪ
    -0.07
     parlam
    -0.07
     missed
    -0.06
    elden
    -0.06
    POSITIVE LOGITS
     disclaimer
    0.12
    Disclaimer
    0.12
     Disclaimer
    0.11
    ä¸į代表
    0.10
     copyright
    0.09
    ä¸įæŀĦæĪIJ
    0.09
     copyrighted
    0.09
    并ä¸į代表
    0.09
    æľªç»ı许åı¯
    0.09
    çīĪæĿĥå½Ĵ
    0.09
    Activations Density 1.487%

    No Known Activations