© 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. 13340
    Prev
    Next
    INDEX
    Explanations

    retired, completed, or solved

    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
    åIJ¸å¼ķçĿĢ
    -0.07
    åľ¨è¿Ļ个æŶåĢĻ
    -0.07
    entine
    -0.07
    èĢĮæѤæŶ
    -0.07
    æīįå¼Ģå§ĭ
    -0.07
     desperately
    -0.07
    .AttributeSet
    -0.07
    襲
    -0.07
    æľīæľº
    -0.07
    quake
    -0.07
    POSITIVE LOGITS
    ç»ĵæ¡Ī
    0.09
    åİĨæŶ
    0.08
    ä¸įäºĨäºĨ
    0.08
     satisfactory
    0.08
    æľĢç»ĪçļĦ
    0.07
    æľĢçµĤ
    0.07
     resolved
    0.07
     erled
    0.07
    å·²äºİ
    0.07
    åĬŀç»ĵ
    0.07
    Activations Density 0.303%

    No Known Activations