© 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. 38936
    Prev
    Next
    INDEX
    Explanations

    data access optimizations

    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
     Unters
    -0.08
    corp
    -0.07
    ç»ıæµİæĬĢæľ¯
    -0.07
    褪
    -0.07
    azah
    -0.07
    arduino
    -0.06
    MENU
    -0.06
    åį±
    -0.06
    Specifier
    -0.06
    çĶ·å¥³ä¸įéĻIJ
    -0.06
    POSITIVE LOGITS
     optimizations
    0.13
     efficiently
    0.12
     optimize
    0.11
     cache
    0.11
    é«ĺæķĪ
    0.10
     inefficient
    0.10
    cache
    0.10
     optimization
    0.10
     efficient
    0.10
     optimized
    0.10
    Activations Density 0.186%

    No Known Activations