© 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. 39992
    Prev
    Next
    INDEX
    Explanations

    combination

    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
    ikal
    -0.08
    icoli
    -0.08
    itore
    -0.08
    imo
    -0.07
    åIJĦæī§
    -0.07
    ohan
    -0.07
    ä¸įçĿĢ
    -0.06
    ollo
    -0.06
    ndx
    -0.06
    iato
    -0.06
    POSITIVE LOGITS
    ä¸įåIJĮ
    0.10
    æĹ¢
    0.10
     ÑĢазнÑĭÑħ
    0.10
    ä¸įåIJĮçļĦ
    0.10
    çļĦä¸įåIJĮ
    0.09
     different
    0.09
    æĹ¢æĺ¯
    0.09
     lẫn
    0.09
    æĹ¢æľī
    0.09
     diferentes
    0.09
    Activations Density 0.541%

    No Known Activations