© 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. 50528
    Prev
    Next
    INDEX
    Explanations

    counts and statistics

    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
    å¤ļåIJĥä¸ĢäºĽ
    -0.08
    åıijçĶŁéĩį大
    -0.07
    abay
    -0.07
    å¤§ä½ľ
    -0.07
    orario
    -0.07
    udz
    -0.07
    ä¸Ĭå½ĵ
    -0.07
    _ghost
    -0.07
    zam
    -0.07
    æľīå¾Ī大çļĦ
    -0.07
    POSITIVE LOGITS
    ä¹ĭå¤ļ
    0.09
    ç»Ĩå¾®
    0.08
    oga
    0.08
    大大å°ıå°ıçļĦ
    0.07
    è¿ĻäºĽå°ı
    0.07
    dot
    0.07
    综
    0.07
    åĮºåĮº
    0.07
    åĹ½
    0.07
     (!
    0.07
    Activations Density 0.664%

    No Known Activations