© 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. 22468
    Prev
    Next
    INDEX
    Explanations

    academic curriculum and subjects

    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
    è¿Ļç§įè¡Į为
    -0.08
    ä¹łæĥ¯æĢ§
    -0.08
    天æĺİ
    -0.08
    个人è¡Į为
    -0.07
     UNU
    -0.07
    åıĤä¸İæ´»åĬ¨
    -0.07
    åħ¶è¡Į为
    -0.07
    å¥
    -0.07
    ä¿¡çĶ¨çŃī级
    -0.07
    æł©æł©
    -0.07
    POSITIVE LOGITS
    ä¸īéŨ
    0.10
    å¿ħä¿®
    0.10
    ç§ij缮
    0.09
    åĨħ容åĴĮ
    0.09
    大纲
    0.09
     elective
    0.09
     compulsory
    0.09
     пÑĢедмеÑĤов
    0.09
     subjects
    0.09
     content
    0.09
    Activations Density 0.072%

    No Known Activations