© 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. 33240
    Prev
    Next
    INDEX
    Explanations

    movie titles

    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
    åĢ¡å¯¼
    -0.07
    oday
    -0.07
    è°Ĭ
    -0.07
    owitz
    -0.07
    ä¿ĿæĮģèī¯å¥½çļĦ
    -0.07
    åħ¨çĽĺ
    -0.07
    glas
    -0.07
    lieb
    -0.07
    ijn
    -0.07
    å¼Ĥä½į
    -0.06
    POSITIVE LOGITS
    çĭ¬ç«ĭå®ĮæĪIJ
    0.07
    ä¸ģé¦Ļ
    0.07
    èĥĮå½±
    0.07
    ä¸ŃæĸŃ
    0.07
    åĩłæ¬¡
    0.06
    示æĦı
    0.06
     اÙĦÙģÙĨÙĬØ©
    0.06
    isu
    0.06
    æķħäºĭæĥħèĬĤ
    0.06
    姥
    0.06
    Activations Density 0.003%

    No Known Activations