© 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. 50876
    Prev
    Next
    INDEX
    Explanations

    not just

    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
    并ä¸įæĺ¯
    -0.08
    并ä¸įèĥ½
    -0.08
    rå
    -0.08
    并ä¸įçŁ¥éģĵ
    -0.08
    并ä¸į
    -0.07
    并ä¸įä¼ļ
    -0.07
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    -0.07
    estre
    -0.07
    è¿ĩæĹ©
    -0.07
     forth
    -0.07
    POSITIVE LOGITS
    å¼ģ
    0.08
     بÙĦÚ©Ùĩ
    0.08
    تÙĩا
    0.08
     sondern
    0.08
     ÙģØŃسب
    0.07
    arg
    0.07
    ersh
    0.07
    .att
    0.07
    å°±ç®ĹäºĨ
    0.07
    èĢĮæĺ¯
    0.07
    Activations Density 0.138%

    No Known Activations