© 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. 25772
    Prev
    Next
    INDEX
    Explanations

    even and odd rows

    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
     suku
    -0.08
    {text
    -0.08
    ä¸Ģå¸Ĩ
    -0.08
    kout
    -0.08
    æĿ¥ä¹ĭ
    -0.08
    æĭ·è´Ŀ
    -0.08
    /Web
    -0.08
    tav
    -0.07
     testim
    -0.07
     libertin
    -0.07
    POSITIVE LOGITS
    checker
    0.08
    Ïģιά
    0.07
    缸éĤ»
    0.07
    æŃ»æ´»
    0.07
    å¥ĩ
    0.07
    Checker
    0.07
    ç½ijæł¼
    0.07
     подÑģ
    0.07
     checker
    0.07
     odd
    0.07
    Activations Density 0.005%

    No Known Activations