© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39456
    Prev
    Next
    INDEX
    Explanations

    code language constructs

    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
    ä¸įçĶ¨è¯´
    -0.08
    ä¸įéĻIJäºİ
    -0.07
     instead
    -0.07
    ([$
    -0.07
    ä¸įèĩª
    -0.07
    ä¸įèĥľ
    -0.07
    ä¸įæĺ¯ä¸ºäºĨ
    -0.07
    adel
    -0.07
    èĻ½å°ı
    -0.07
     nicht
    -0.06
    POSITIVE LOGITS
     anymore
    0.11
     nor
    0.11
    èĢĮæĺ¯
    0.09
     sondern
    0.09
    หรà¸Ńà¸ģ
    0.08
     οÏįÏĦε
    0.08
    æľīä»»ä½ķ
    0.08
    ä½Ĩåı¯ä»¥
    0.08
     Ø¥ÙĦا
    0.08
     melainkan
    0.08
    Activations Density 0.046%

    No Known Activations