© 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. 48779
    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
    åIJĦè¡ĮåIJĦ
    -0.08
    ç©Ĩæĸ¯
    -0.08
    acon
    -0.08
    æ·±æ·±åľ°
    -0.07
    ambul
    -0.07
    \AppData
    -0.07
    à¹Īย
    -0.07
    å½»
    -0.07
    коÑĢа
    -0.07
    FAULT
    -0.07
    POSITIVE LOGITS
    èĢħä¼ĺåħĪ
    0.08
    allest
    0.07
    åģıçĪ±
    0.07
     favors
    0.07
    åºŁè¯Ŀ
    0.07
    inare
    0.06
    大æ´ĭ
    0.06
    пода
    0.06
    ä¹Łæĺ¯æľĢ
    0.06
     favored
    0.06
    Activations Density 0.000%

    No Known Activations