© 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. 19096
    Prev
    Next
    INDEX
    Explanations

    math and code syntax

    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
    ients
    -0.08
    åįķæĭĽ
    -0.07
    建åĪ¶
    -0.07
    anford
    -0.07
    èģĮä¸ļåѦéĻ¢
    -0.07
    fds
    -0.07
    åĴĮåİ¿
    -0.06
     Pemer
    -0.06
    .fa
    -0.06
    认
    -0.06
    POSITIVE LOGITS
     cấp
    0.08
    acic
    0.07
    ä¸ī级
    0.07
    æݧ
    0.07
    åĪĨåĪ«æĺ¯
    0.07
    zan
    0.07
    æľĢ主è¦ģ
    0.07
    æĸ¯åŁº
    0.06
    ä¸Ģ级
    0.06
    াà¦Ĺ
    0.06
    Activations Density 0.041%

    No Known Activations