© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20700
    Prev
    Next
    INDEX
    Explanations

    modernizing style and concepts

    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
    åĢĴéľī
    -0.07
    ãĥ©ãĤ¤
    -0.06
     final
    -0.06
    åĽ´ç»ķçĿĢ
    -0.06
    ä½³
    -0.06
    æīĢå±ŀè¡Įä¸ļ
    -0.06
    æľĢç»ĪçļĦ
    -0.06
     depos
    -0.06
    ä¸įåİ»
    -0.06
    çĽ¯çĿĢ
    -0.06
    POSITIVE LOGITS
     modern
    0.14
     Modern
    0.14
    Modern
    0.14
    çļĦçݰ代
    0.13
    çı¾ä»£
    0.13
    modern
    0.13
    çݰ代
    0.13
    çݰ代åĮĸ
    0.12
    èŀįåIJĪ
    0.12
    ä¸İçݰ代
    0.11
    Activations Density 0.224%

    No Known Activations