© 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. 30479
    Prev
    Next
    INDEX
    Explanations

    rivers and streams

    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
    æĿIJæĸĻ
    -0.07
    è¿Ļæī¹
    -0.06
     ÑĪÑĤа
    -0.06
     rocking
    -0.06
    æł©æł©
    -0.06
    éĻIJä»·
    -0.06
    åıįéĿ¢
    -0.06
    æ¯ı项
    -0.06
    èĢIJçĥŃ
    -0.06
    åıĸåIJij
    -0.06
    POSITIVE LOGITS
    æĶ¯æµģ
    0.13
    æ±ĩåħ¥
    0.13
    åIJĮåIJį
    0.12
    æºIJ头
    0.11
    æµģç»ı
    0.11
    æµģéĩıçļĦ
    0.11
    æµģéĩı
    0.10
     runoff
    0.10
     streams
    0.10
     branches
    0.10
    Activations Density 0.170%

    No Known Activations