© 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. 60619
    Prev
    Next
    INDEX
    Explanations

    now then

    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
     currently
    -0.10
    缮åīįæŃ£åľ¨
    -0.08
     initially
    -0.08
     actuellement
    -0.08
     actualmente
    -0.08
    缮åīįå·²ç»ı
    -0.08
    èĩ³ä»Ĭ
    -0.08
     ultimately
    -0.08
    èĩ³ä»Ĭä»į
    -0.08
    currently
    -0.08
    POSITIVE LOGITS
    æľīäºĨä¸Ģ个
    0.11
    æľīäºĨ
    0.10
    ä¸Ģæł·äºĨ
    0.10
    éĹ®é¢ĺæĿ¥äºĨ
    0.10
    ä¸įåIJĮäºĨ
    0.10
    ä¹ŁæľīäºĨ
    0.10
    ä¸įåĨįæĺ¯
    0.10
     ìĿ´ìłľ
    0.09
    éĹ®é¢ĺäºĨ
    0.09
     ТепеÑĢÑĮ
    0.09
    Activations Density 0.086%

    No Known Activations