© 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. 3241
    Prev
    Next
    INDEX
    Explanations

    training requirements

    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
    å¾ĹçĽĬäºİ
    -0.08
    è¦ģå°ıå¿ĥ
    -0.08
    轻轻ä¸Ģ
    -0.07
    fér
    -0.07
    æĬķèµĦæľºä¼ļ
    -0.07
    ä¿¡ä»»
    -0.07
    åIJĪåIJĮæŶ
    -0.07
    èĩªæĿ¥
    -0.07
    estina
    -0.07
     graças
    -0.07
    POSITIVE LOGITS
    ä¸įå°ijäºİ
    0.15
    ä¸įä½İäºİ
    0.14
    èĩ³å°ij
    0.14
    èĩ³å°ijåľ¨
    0.14
    ä¸įå¾Ĺä½İäºİ
    0.13
    ä¸įå¾Ĺ
    0.13
     almeno
    0.12
    å°ijãģªãģıãģ¨ãĤĤ
    0.11
    èĩ³å°ijè¦ģ
    0.11
    èĩ³å°ijæľī
    0.11
    Activations Density 0.109%

    No Known Activations