© 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. 26175
    Prev
    Next
    INDEX
    Explanations

    contrast and difference

    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
    èĢĮä¸įæĺ¯
    -0.11
    èĢĮéĿŀ
    -0.10
    æ¯Ķåħ¶ä»ĸ
    -0.09
    æ¯ĶæĻ®éĢļ
    -0.09
    кÑĤи
    -0.08
     rather
    -0.08
     piuttosto
    -0.08
    æ¯Ķ以å¾Ģ
    -0.08
    èĢĮåħ¶ä»ĸ
    -0.08
    rather
    -0.08
    POSITIVE LOGITS
    ãģĵãģ¡ãĤīãģ¯
    0.12
     dagegen
    0.10
     comparatively
    0.10
    没æľīéĤ£ä¹Ī
    0.10
    åIJĮæł·çļĦ
    0.08
    没éĤ£ä¹Ī
    0.08
    缸åıį
    0.08
     hingegen
    0.08
    æĽ´æ³¨éĩį
    0.08
    å¾Ĺå¤ļ
    0.08
    Activations Density 0.106%

    No Known Activations