© 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. 63827
    Prev
    Next
    INDEX
    Explanations

    preparing for access or improvement

    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
    éĤ£éĩĮçļĦ
    -0.08
    éĤ£ä¸įæĺ¯
    -0.08
    аÑĤÑĥ
    -0.07
    éĤ£åľº
    -0.07
    кладÑĭ
    -0.07
    è¿Ļæĸ¹éĿ¢çļĦ
    -0.07
    è¿Ļæĸ¹éĿ¢
    -0.07
    请åĬł
    -0.07
    没æľīéĤ£ä¹Ī
    -0.07
    éĤ£ä¹Łæĺ¯
    -0.07
    POSITIVE LOGITS
    æİ¥ä¸ĭæĿ¥
    0.10
    ä¸ĭæĸĩ
    0.09
    ä¸ĭåIJĮ
    0.08
     ready
    0.08
    ä¸ĭä¸ĢæŃ¥
    0.08
    åĩĨå¤ĩ
    0.08
    æİ¥ä¸ĭæĿ¥çļĦ
    0.08
     ì¤Ģë¹Ħ
    0.08
     Grundlage
    0.08
     preparing
    0.07
    Activations Density 0.068%

    No Known Activations