© 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. 48527
    Prev
    Next
    INDEX
    Explanations

    imaging, eCommerce, women, camp, transplantation, screening, sports, developmental

    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
    ä¸įçĶĺå¿ĥ
    -0.07
    apl
    -0.07
    -Za
    -0.07
    ä»ĻåŃIJ
    -0.07
    ORTE
    -0.07
    isser
    -0.07
    ulong
    -0.07
    одо
    -0.06
    峪
    -0.06
    ä¸įçĶĺ
    -0.06
    POSITIVE LOGITS
    ä¸İæĻ®éĢļ
    0.07
    éd
    0.07
    åĴĮæĻ®éĢļ
    0.07
     ìłĦìļ©
    0.07
    ä¸ĵçĶ¨
    0.07
    quirer
    0.07
    ØŃتÙĩا
    0.06
    æ¯ĶæĻ®éĢļ
    0.06
    è§ī
    0.06
    æĹłéĿŀ
    0.06
    Activations Density 0.690%

    No Known Activations