© 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. 1850
    Prev
    Next
    INDEX
    Explanations

    -k expressions

    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
    awa
    -0.07
    åIJ®
    -0.06
    èIJį
    -0.06
    liz
    -0.06
     preamble
    -0.06
    ãģĿãĤį
    -0.06
    个人éļIJç§ģ
    -0.06
    æķ´ä¸ªä¸ĸçķĮ
    -0.06
    uchs
    -0.06
    èĬ±æł·
    -0.06
    POSITIVE LOGITS
    çŀŃ
    0.08
    á»Ńng
    0.08
    vist
    0.08
    ousel
    0.08
    dür
    0.08
    élo
    0.08
    ç¥ĸ
    0.07
    ç§įåħ»
    0.07
    NIS
    0.07
    rese
    0.07
    Activations Density 0.003%

    No Known Activations