© 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. 47568
    Prev
    Next
    INDEX
    Explanations

    names and professions

    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
    à¸ĺรรมà¸Ĭาà¸ķิà¹ģละ
    -0.09
    สà¸Ļุà¸ģà¹ģละ
    -0.09
    ading
    -0.08
    温æļĸåĴĮ
    -0.08
    éĶĢåĶ®åĴĮ
    -0.08
    Authenticated
    -0.08
    ÑħÑĤа
    -0.08
    è´¨éĩıåĴĮ
    -0.07
    ysten
    -0.07
    ysters
    -0.07
    POSITIVE LOGITS
    èĢĮéĤ£
    0.08
    ä¹ħä¹ĭ
    0.07
     assisted
    0.06
    æĻĤãģ«ãģ¯
    0.06
    r
    0.06
     shared
    0.06
     avoiding
    0.06
     eventual
    0.06
    åĬ©äºİ
    0.06
    åĪ©äºİ
    0.06
    Activations Density 0.138%

    No Known Activations