© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2509
    Prev
    Next
    INDEX
    Explanations

    cardiovascular disease risk, insertion, building information, electrical stimulation, preserving information

    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
    cec
    -0.09
    ).(
    -0.08
    ä¸ĭåIJĮ
    -0.08
    )..
    -0.08
    akaan
    -0.08
     invece
    -0.08
     Rosenstein
    -0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.07
     Nego
    -0.07
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    POSITIVE LOGITS
     sogenannten
    0.10
     sogenannte
    0.09
     ìŀĪëĬĶëį°
    0.09
     _______,
    0.08
    ãģĹãģ¾ãģĻãģĮ
    0.08
     sogen
    0.08
    å¾Ī大ç¨ĭ度ä¸Ĭ
    0.08
     ìŀĪëĬĶëį°ìļĶ
    0.08
    å¾Īå¤ļä¸ľè¥¿
    0.08
    ãģĦãģ¾ãģĻãģĮ
    0.08
    Activations Density 0.790%

    No Known Activations