© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 29518
    Prev
    Next
    INDEX
    Explanations

    Draw or just action

    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
    ihar
    -0.07
    ium
    -0.07
    æ§Ľ
    -0.07
    æĪĸåĽł
    -0.07
    ugi
    -0.07
    ä¸įæĺ¯åĽłä¸º
    -0.07
    æ±Ĺ
    -0.07
    ooks
    -0.07
    转载æĪĸ
    -0.07
    ampu
    -0.06
    POSITIVE LOGITS
    缴æİ¥ç͍
    0.09
    缴æİ¥åľ¨
    0.08
    缴æİ¥æĬĬ
    0.08
    å°±ç͍
    0.07
    å°±ä¸Ģ缴
    0.07
    eldon
    0.07
     using
    0.07
    à¸Ĭี
    0.07
    æĬĬæīĢæľīçļĦ
    0.07
    åĪļä¸Ģ
    0.07
    Activations Density 0.157%

    No Known Activations