© 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. 12572
    Prev
    Next
    INDEX
    Explanations

    directory paths or coding 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
    nya
    -0.11
    ä½Ĩä¸įéĻIJäºİ
    -0.10
    Allem
    -0.09
    FONT
    -0.09
     ë¶Ī구íķĺê³ł
    -0.09
    ï¸İ
    -0.09
    ically
    -0.08
    zinho
    -0.08
    çļĦãģ«
    -0.08
    rhein
    -0.08
    POSITIVE LOGITS
    รษ
    0.11
    à¹ĭ
    0.08
    (qu
    0.08
    wards
    0.08
    ../../../
    0.08
    æĹłè¸ª
    0.08
    äºĨä¸Ģ
    0.07
    ếm
    0.07
    äºĨä¸Ģåľº
    0.07
    inheit
    0.07
    Activations Density 0.003%

    No Known Activations