© 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. 51118
    Prev
    Next
    INDEX
    Explanations

    US patent numbers

    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
     تعاÙĦÙī
    -0.08
    vrier
    -0.08
    ansson
    -0.08
    iola
    -0.08
    żeli
    -0.07
    _tuples
    -0.07
    vard
    -0.07
    undry
    -0.07
    пÑĭÑĤ
    -0.07
    leden
    -0.07
    POSITIVE LOGITS
    mehr
    0.08
    ograd
    0.08
    orrow
    0.07
    ä¸įä¼ij
    0.07
    æ»ļæ»ļ
    0.07
    ÙĪعات
    0.07
    èĬ³åįİ
    0.07
    ousel
    0.06
    å¤ŁäºĨ
    0.06
    alb
    0.06
    Activations Density 0.672%

    No Known Activations