© 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. 49849
    Prev
    Next
    INDEX
    Explanations

    ratio, rate, relative, efficiency, occupancy

    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
     Mansion
    -0.09
    kest
    -0.08
    ä¸įä¿¡
    -0.08
    blick
    -0.08
    usted
    -0.07
    æĺ¥åįİ
    -0.07
    INCREMENT
    -0.07
    .endsWith
    -0.07
     âĸij
    -0.07
    å¢ŀè¿Ľ
    -0.07
    POSITIVE LOGITS
    å®ļä¹ī为
    0.08
    è¡¡
    0.08
    urut
    0.07
     ratio
    0.07
    ratio
    0.07
    Clr
    0.07
     Defined
    0.07
    å¾Ĵ
    0.07
     defined
    0.07
    asio
    0.07
    Activations Density 0.018%

    No Known Activations