© 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. 49231
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    为转载
    -0.08
     zuk
    -0.07
    åĽł
    -0.07
    olib
    -0.07
    —even
    -0.07
    ile
    -0.07
    ycl
    -0.07
    row
    -0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    -0.07
    èĩªæĪijä¿ĿæĬ¤
    -0.07
    POSITIVE LOGITS
    menti
    0.07
    zah
    0.06
    æī©å±ķèµĦæĸĻ
    0.06
     Paso
    0.06
    ignan
    0.06
    _parms
    0.06
    æĪijåIJ¬
    0.06
    å¿Ļäºİ
    0.06
    ocard
    0.06
    двига
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.