© 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. 61358
    Prev
    Next
    INDEX
    Explanations

    condition or status of being

    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
    umpf
    -0.10
    velt
    -0.08
    åħ¶ä»ĸ类似éĹ®é¢ĺ
    -0.07
    asa
    -0.07
    пÑĤи
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    象
    -0.07
    itter
    -0.07
     kaum
    -0.07
    åĪĨä¼ļ
    -0.07
    POSITIVE LOGITS
    æĮĩçļĦæĺ¯
    0.08
    ä¹Łå°±æĺ¯è¯´
    0.08
    ÛĮع
    0.08
     specifically
    0.07
    çļĦæĦıæĢĿæĺ¯
    0.07
    æĦıåij³çĿĢ
    0.07
    æĦıæĢĿæĺ¯
    0.07
    æĺ¯ä»Ģä¹ĪæĦıæĢĿ
    0.07
    è¿ĻæĦıåij³çĿĢ
    0.07
     หมายà¸ĸึà¸ĩ
    0.07
    Activations Density 0.001%

    No Known Activations