© 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. 51244
    Prev
    Next
    INDEX
    Explanations

    us is

    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
    è¿ŀåŁİ
    -0.07
    æĹłèĻij
    -0.07
    лек
    -0.06
    rozum
    -0.06
    _export
    -0.06
    åį±éĻ©åĽłç´ł
    -0.06
    çŃ
    -0.06
    cej
    -0.06
    rcode
    -0.06
     conosco
    -0.06
    POSITIVE LOGITS
    arro
    0.09
    æݢ究
    0.07
    olas
    0.07
     mithilfe
    0.07
     iam
    0.07
    åĽ½å¼º
    0.06
    оÑĢг
    0.06
    dá
    0.06
    mlx
    0.06
    arra
    0.06
    Activations Density 0.027%

    No Known Activations