© 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. 25817
    Prev
    Next
    INDEX
    Explanations

    by definition, virtue, tradition

    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
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.08
    ç®Ĺä»Ģä¹Ī
    -0.07
    cgi
    -0.07
    å¨ĵ
    -0.07
    ubro
    -0.07
    解æĶ¾
    -0.07
    绣èĬ±
    -0.07
    øgne
    -0.07
    olino
    -0.07
    .codes
    -0.07
    POSITIVE LOGITS
    éģĵçIJĨ
    0.09
     definition
    0.08
    é¢ĺæĦı
    0.08
    agher
    0.08
     virtue
    0.08
    设计è¦ģæ±Ĥ
    0.07
    éĢīæĭ©ä¸įåIJĮçļĦ
    0.07
     tradition
    0.07
    çĦ¶æĺ¯
    0.07
    elos
    0.07
    Activations Density 0.035%

    No Known Activations