© 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. 45838
    Prev
    Next
    INDEX
    Explanations

    achieved through

    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
    为äºĨæĽ´å¥½çļĦ
    -0.07
    osso
    -0.07
    为äºĨ
    -0.06
    ÙĪÙĨت
    -0.06
    åıªä¸º
    -0.06
    èµ·åĽł
    -0.06
    æĽ´èĥ½
    -0.06
    æĺ¯ä¸ºäºĨ
    -0.06
    为äºĨä¿ĿæĬ¤
    -0.06
     sill
    -0.06
    POSITIVE LOGITS
    åħ¶ä»ĸæĸ¹å¼ı
    0.12
    éĢļè¿ĩåľ¨
    0.11
    éĢļè¿ĩ对
    0.11
    éĢļè¿ĩå°Ĩ
    0.10
    å¤ļç§įæĸ¹å¼ı
    0.09
    éĢļè¿ĩä¸İ
    0.09
     through
    0.09
    through
    0.09
    çļĦä¸Ģç§įæĸ¹å¼ı
    0.09
     sheer
    0.09
    Activations Density 0.225%

    No Known Activations