© 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. 27821
    Prev
    Next
    INDEX
    Explanations

    not only

    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
    egger
    -0.08
     Extras
    -0.08
    åģļçļĦæĺ¯
    -0.07
    ož
    -0.07
    ç¬ijçĿĢ说éģĵ
    -0.07
    å¤ļæľĪ
    -0.07
    临æŶèĤ¡ä¸ľå¤§ä¼ļ
    -0.07
    æķ´ä½ĵä¸Ĭ
    -0.06
    çĽ¸å¯¹èĢĮè¨Ģ
    -0.06
    iola
    -0.06
    POSITIVE LOGITS
    ä¸įä»ħä»ħ
    0.08
    cel
    0.08
    ä¼łç»ŁçļĦ
    0.08
    æĻ®éĢļçļĦ
    0.08
    chend
    0.08
    åįķ纯çļĦ
    0.08
    åİŁæľ¬çļĦ
    0.08
    æŃ£å¼ı
    0.08
    åįķ纯
    0.08
     mere
    0.08
    Activations Density 0.239%

    No Known Activations