© 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. 33352
    Prev
    Next
    INDEX
    Explanations

    product-form solution

    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
    empat
    -0.08
    ä¼łå¯¼
    -0.07
    ä¸įæĸ¹ä¾¿
    -0.07
    skr
    -0.07
    åĽĽçº§
    -0.07
    åĢ¼æѤ
    -0.07
     Deja
    -0.07
     appréci
    -0.07
     Chec
    -0.07
    ipher
    -0.07
    POSITIVE LOGITS
    æľĢä¼ĺ
    0.09
     optimal
    0.09
    æĺ¯æľĢ
    0.08
    æľĢéģ©
    0.08
     optimum
    0.08
     uniqueness
    0.07
     maximizing
    0.07
    æĺ¯åĶ¯ä¸Ģ
    0.07
    ä¹Łæĺ¯æľĢ
    0.07
    ivel
    0.07
    Activations Density 0.010%

    No Known Activations