© 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. 50931
    Prev
    Next
    INDEX
    Explanations

    previous work or recent findings

    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
    ä½łè¯´çļĦ
    -0.08
    uen
    -0.07
    æīĭåĨĮ
    -0.07
    èĩªåı¤ä»¥æĿ¥
    -0.07
    æĶ¾
    -0.07
    æ¿Ģ
    -0.06
    رج
    -0.06
    åĨĮ
    -0.06
     central
    -0.06
     веÑī
    -0.06
    POSITIVE LOGITS
    åĵŃç¬ij
    0.08
    éģĵè¿ľ
    0.08
     اÙĦÙĪج
    0.08
    {@
    0.08
     íĽ¨
    0.08
    uju
    0.08
    éĤ£æĺ¯æĪij
    0.08
    gian
    0.08
    пÑı
    0.08
    à¸ķà¹Ī
    0.08
    Activations Density 0.276%

    No Known Activations