© 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. 43907
    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
    __/
    -0.06
     Humph
    -0.06
    èĩªå·±çļĦåĬĽéĩı
    -0.06
    èªĮ
    -0.06
    rog
    -0.06
    æŃ³
    -0.06
    ellow
    -0.06
    ÑĤиÑĢа
    -0.06
    nict
    -0.06
    åĬĽ
    -0.06
    POSITIVE LOGITS
    ToArray
    0.08
    bnb
    0.08
    åįĬæľĪ
    0.08
    resto
    0.07
    hev
    0.07
    WithContext
    0.07
    è¯Ńè¨Ģ表达
    0.07
    Concat
    0.07
    OLON
    0.07
    ìĸ¸
    0.07
    Activations Density 0.000%

    No Known Activations