© 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. 12228
    Prev
    Next
    INDEX
    Explanations

    data bytes, visualizations, forms, URLs

    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
    éĩİ
    -0.08
    ä¸ĢçĽ´ä»¥
    -0.07
    è¡Ģ绣
    -0.07
    æľīå¿Ĺ
    -0.07
    å¿Ĺ
    -0.07
    iable
    -0.07
    æĿ¾è½¯
    -0.06
    åIJ¸çº³
    -0.06
     presumed
    -0.06
     loosely
    -0.06
    POSITIVE LOGITS
    产åĵģå±ķ示
    0.09
    èİħ
    0.09
     Auss
    0.08
    åı¯è§ĨåĮĸ
    0.08
    æĪij们çļĦ产åĵģ
    0.08
    æľ¬ç½ij
    0.08
     visualization
    0.08
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.08
    ynes
    0.08
    ä½ľåĵģå±ķ
    0.08
    Activations Density 0.317%

    No Known Activations