© 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. 37948
    Prev
    Next
    INDEX
    Explanations

    search, research, adaptive, binary search trees

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    çļĦç»ıæµİ
    -0.08
     رس
    -0.08
    oon
    -0.07
    ä¿ĬæĿ°
    -0.07
    baru
    -0.07
    á»ĩ
    -0.07
    hluk
    -0.07
    åij±åij±
    -0.07
    ivers
    -0.07
    POSITIVE LOGITS
    verfahren
    0.07
    pil
    0.07
    æ±Ĥ
    0.07
    æ¼ĶæĬĢ
    0.07
    estroy
    0.06
    大æ³ķ
    0.06
    æľºä¼ļ
    0.06
    egger
    0.06
    ed
    0.06
    ä¸ĬåİķæīĢ
    0.06
    Activations Density 0.003%

    No Known Activations