© 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. 2894
    Prev
    Next
    INDEX
    Explanations

    jQuery, parse, imaging, wavelengths

    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
    _generic
    -0.08
    à¹īำ
    -0.07
     Pue
    -0.07
    kc
    -0.07
    Ĵ
    -0.07
    è¿Ľä¸ĢæŃ¥å®ĮåĸĦ
    -0.07
    ROP
    -0.07
    гал
    -0.07
    миÑĤе
    -0.07
     Kee
    -0.07
    POSITIVE LOGITS
    缴è§Ĥ
    0.08
    缴è§ī
    0.07
     intuitive
    0.07
    ãĤĦãĤĬãģŁãģĦ
    0.07
    缴è§ĤçļĦ
    0.07
     intuit
    0.06
    ugn
    0.06
    stal
    0.06
    æĤ£
    0.06
    -hidden
    0.06
    Activations Density 0.344%

    No Known Activations