© 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. 32393
    Prev
    Next
    INDEX
    Explanations

    code assignment or mapping

    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
    åı¯æĺ¯ä»ĸ
    -0.09
    éĤ£ä»ĸ
    -0.09
    æīĢ以ä»ĸ们
    -0.09
    ä½Ĩæĺ¯å¯¹äºİ
    -0.09
    ä½Ĩèĩ³å°ij
    -0.08
    ä½Ĩæĺ¯ä»ĸ们
    -0.08
    èĢĮéĤ£äºĽ
    -0.08
    ä½Ĩæĺ¯ä»ĸ
    -0.08
    ä½Ĩæĺ¯ä½ł
    -0.08
    äºİæĺ¯ä»ĸ
    -0.08
    POSITIVE LOGITS
    i
    0.09
    ï¸ı
    0.08
    ://
    0.08
    nya
    0.07
    emente
    0.07
    ï¼ļ
    0.07
    es
    0.07
    ÄĻ
    0.07
    ,//
    0.07
    Ø©
    0.07
    Activations Density 0.003%

    No Known Activations