© 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. 25966
    Prev
    Next
    INDEX
    Explanations

    technical methodology and design

    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
    ä¸ĭè§Ĵ
    -0.07
    urr
    -0.07
    éĴ¦
    -0.06
    æĢ»ä½ĵä¸Ĭ
    -0.06
    大ä¼ļä¸Ĭ
    -0.06
    缮æłĩä»»åĬ¡
    -0.06
    ä¸ĭ游
    -0.06
    ongyang
    -0.06
    éĿ©
    -0.06
    мой
    -0.06
    POSITIVE LOGITS
    ä¸ĢæŃ¥æŃ¥
    0.09
     methodology
    0.08
    -cal
    0.08
    cal
    0.07
    è¿IJçĶ¨äºĨ
    0.07
    ysel
    0.07
    rim
    0.07
    ä»Ģä¹ĪçļĦ
    0.07
    _method
    0.07
    boro
    0.07
    Activations Density 0.003%

    No Known Activations