© 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. 39007
    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
    gree
    -0.07
    .cross
    -0.07
    ãģ¤ãģı
    -0.07
    تÙĦ
    -0.07
    _CHO
    -0.07
    çĮ¬
    -0.07
    chet
    -0.07
    è¿Ļèµ·
    -0.07
    è¿Ŀåıįä¸Ĭè¿°
    -0.07
    ilton
    -0.07
    POSITIVE LOGITS
    гал
    0.07
    зан
    0.07
    olini
    0.07
    Sm
    0.07
    æķĻåĮĸ
    0.06
    PS
    0.06
     gang
    0.06
    Ñģне
    0.06
    ç³Ł
    0.06
     won
    0.06
    Activations Density 0.000%

    No Known Activations