© 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. 31442
    Prev
    Next
    INDEX
    Explanations

    actions depicted in media

    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
    akov
    -0.08
    åľ¨æ¯ı个
    -0.08
    å°Ĩè¿Ļ
    -0.08
    对äºİè¿ĻäºĽ
    -0.08
     ÑģкладÑĭ
    -0.07
    ilater
    -0.07
    è¿ĻäºĽæķ°æį®
    -0.07
    æ¯ı个åŃ©åŃIJ
    -0.07
    åľ¨è¿ĻäºĽ
    -0.07
    åįĬåĬŁ
    -0.07
    POSITIVE LOGITS
     circa
    0.07
    кÑĤ
    0.07
    mind
    0.06
    天èµIJ
    0.06
    wet
    0.06
    wy
    0.06
    æķ´çIJĨ
    0.06
    ule
    0.06
     McB
    0.06
    æijĦ
    0.06
    Activations Density 0.188%

    No Known Activations