© 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. 29790
    Prev
    Next
    INDEX
    Explanations

    abstract, impressionist, and minimalist art

    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
    åĿıä¹łæĥ¯
    -0.07
    Å¡ov
    -0.07
    minate
    -0.07
    æ¯Ļ
    -0.07
    letcher
    -0.07
    ÑģообÑĢаз
    -0.07
    ä¸įèĭŁ
    -0.07
     curiositÃł
    -0.07
    Chocolate
    -0.07
    çĶŁç´ł
    -0.07
    POSITIVE LOGITS
    ,color
    0.07
    客è§Ĥ
    0.07
    ê°±
    0.07
     Cab
    0.07
    NJ
    0.07
    æ£Ĵ
    0.07
    Cab
    0.07
     Kata
    0.07
    æĮª
    0.06
    æĦıåIJij
    0.06
    Activations Density 0.016%

    No Known Activations