© 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. 28582
    Prev
    Next
    INDEX
    Explanations

    lots of new features

    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
    åIJĮæŶè¦ģ
    -0.08
    precated
    -0.07
    åIJĮæŶ
    -0.07
    antan
    -0.07
     ggf
    -0.07
    æľīåı¯èĥ½
    -0.07
    à¹Ģà¸Ļ
    -0.06
    Õ¡Õ®
    -0.06
     ÙħØ«ÙĦا
    -0.06
    κο
    -0.06
    POSITIVE LOGITS
    åĪĨå¸ĥå¦Ĥä¸ĭ
    0.11
    æľī以ä¸ĭ
    0.10
    以ä¸ĭæĺ¯
    0.10
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.10
     ëĭ¤ìĿĮê³¼
    0.09
     à¸Ķัà¸ĩà¸Ļีà¹ī
    0.08
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.08
    以ä¸ĭåĩłä¸ª
    0.08
    ä¸ĭéĿ¢å°±
    0.08
     several
    0.08
    Activations Density 0.458%

    No Known Activations