© 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. 45842
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
    å©ķ
    -0.08
    ä¿®æĶ¹
    -0.07
    oit
    -0.07
    ãs
    -0.07
    notice
    -0.07
    VELO
    -0.07
    èĩ¼
    -0.07
    Notice
    -0.06
    ĸ
    -0.06
    è»Į
    -0.06
    POSITIVE LOGITS
     fetched
    0.08
    大秦
    0.07
    管çIJĨåıĬ
    0.07
    ModuleName
    0.07
    วย
    0.07
    ä¸įåIJĮäºĨ
    0.07
    çĶŁäº§ç»ıèIJ¥
    0.07
     Dread
    0.07
    omad
    0.06
    Allocator
    0.06
    Activations Density 0.005%

    No Known Activations