© 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. 15212
    Prev
    Next
    INDEX
    Explanations

    importance and emphasis

    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
    aver
    -0.09
    itale
    -0.08
    æĶ¾å¿ĥçļĦ
    -0.08
    Äįek
    -0.08
    æľĿ天
    -0.08
    æ³Ĭå°Ķ
    -0.08
    ëĭ¤ëĬĶ
    -0.08
    åı¥è¯Ŀ说
    -0.08
    kata
    -0.07
    å£Į
    -0.07
    POSITIVE LOGITS
    ยà¹īำ
    0.10
     pentingnya
    0.09
     bahwa
    0.08
     rằng
    0.08
    issimi
    0.08
     mẽ
    0.08
    çļĦæĺ¯ä¸Ģ个
    0.08
    ingly
    0.08
    è¿Ļä¸ĢçĤ¹
    0.07
    esz
    0.07
    Activations Density 0.012%

    No Known Activations