© 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. 31757
    Prev
    Next
    INDEX
    Explanations

    macro, header, config, parameters

    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
     concessions
    -0.07
    typeid
    -0.07
    ashi
    -0.07
     hò
    -0.07
    happy
    -0.07
    æģŃåĸľä½ł
    -0.07
     urlparse
    -0.07
    ä¸İä¼Ĺ
    -0.06
    æŁ¥çľĭæīĢæľī
    -0.06
    idy
    -0.06
    POSITIVE LOGITS
    arguments
    0.09
     prepared
    0.08
    åĸĤ
    0.08
     arguments
    0.08
    prepared
    0.08
    串çļĦ
    0.07
    åĩĨå¤ĩ好çļĦ
    0.07
     Argument
    0.07
     argumentos
    0.07
     Arguments
    0.07
    Activations Density 0.357%

    No Known Activations