© 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. 1894
    Prev
    Next
    INDEX
    Explanations

    places and structures

    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
    大å»Ī
    -0.08
    è¡Ĺ头
    -0.07
    èĪ¹ä¸Ĭ
    -0.06
    翱ç¿Ķ
    -0.06
    ä¹ĺé£İçł´æµª
    -0.06
     fluent
    -0.06
    深海
    -0.06
    大åݦ
    -0.06
     flu
    -0.06
    2
    -0.06
    POSITIVE LOGITS
     inhabited
    0.12
     layout
    0.11
    è¿ĻäºĽåľ°æĸ¹
    0.11
    çŃī设æĸ½
    0.11
    æĶ¹å»º
    0.10
     location
    0.10
     layouts
    0.10
     redevelopment
    0.10
    对å¤ĸå¼ĢæĶ¾
    0.10
    æ¯ĹéĤ»
    0.10
    Activations Density 0.693%

    No Known Activations