© 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. 15548
    Prev
    Next
    INDEX
    Explanations

    periodic frequency updates

    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
    ç»ĪæĹ¥
    -0.09
    æĮĩäºĨæĮĩ
    -0.08
    贯彻æī§è¡Į
    -0.08
     enx
    -0.08
    ãģ²ãĤį
    -0.08
    rech
    -0.08
    _LOGGER
    -0.07
     fyr
    -0.07
    born
    -0.07
    æĹ¥å¤ľ
    -0.07
    POSITIVE LOGITS
    ìĶ©
    0.11
    æĽ´æĸ°
    0.10
     Äijặn
    0.10
    å®ļæľŁ
    0.09
    ä¸Ģ次çļĦ
    0.09
     updates
    0.09
    å®ļæľŁçļĦ
    0.08
     update
    0.08
    æĽ´æĸ°çļĦ
    0.08
    ä¸įå®ļæľŁ
    0.08
    Activations Density 0.180%

    No Known Activations