© 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. 45309
    Prev
    Next
    INDEX
    Explanations

    lesions and infections

    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
    izam
    -0.08
    æĺ¯å¾Īæľī
    -0.07
    ocking
    -0.07
     Panas
    -0.07
    积åİĭ
    -0.07
    èĥ
    -0.07
    agy
    -0.07
    bero
    -0.07
    _shell
    -0.07
    è¡¡éĩı
    -0.07
    POSITIVE LOGITS
    çĸijä¼¼
    0.13
     presumed
    0.12
    以为æĺ¯
    0.11
    å¾Īåı¯èĥ½æĺ¯
    0.11
    æľīåı¯èĥ½æĺ¯
    0.11
    æĺ¾çĦ¶æĺ¯
    0.10
    åºĶ该就æĺ¯
    0.10
     suspected
    0.10
    çĸij
    0.09
    ä¼¼ä¹İæĺ¯
    0.09
    Activations Density 0.325%

    No Known Activations