© 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. 16925
    Prev
    Next
    INDEX
    Explanations

    countertops and bearings

    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
    缺ä¸Ģ
    -0.07
     kilos
    -0.07
    建æĪIJåIJİ
    -0.07
    æĬĬè¿Ļ
    -0.07
    ç½®ä¹ĭ
    -0.07
    èĩªæĦĪ
    -0.06
    æĬĬå®ĥ
    -0.06
    unes
    -0.06
    æľīå¾Ī大
    -0.06
    ffre
    -0.06
    POSITIVE LOGITS
    对ä¸ĢäºĽ
    0.12
    åIJĦå¤Ħ
    0.12
    åľ¨åIJĦ个
    0.11
    åIJĦç±»
    0.11
     everywhere
    0.11
    åľ¨åIJĦ
    0.11
     überall
    0.10
     везде
    0.10
    æŁIJäºĽ
    0.10
     ê°ģì¢ħ
    0.10
    Activations Density 0.410%

    No Known Activations