© 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. 64379
    Prev
    Next
    INDEX
    Explanations

    reduce, reduction, reduced

    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
    ually
    -0.09
    uality
    -0.08
    .baidu
    -0.08
    ggi
    -0.07
    irit
    -0.07
    دÙħØ©
    -0.07
    à¸Ķิà¸ļ
    -0.07
    _FUNCTIONS
    -0.07
    adini
    -0.07
    Ī
    -0.07
    POSITIVE LOGITS
     thiá»ĥu
    0.10
     bỼt
    0.09
    jenigen
    0.09
    ä¸įäºĨçļĦ
    0.08
    iamond
    0.08
    AndGet
    0.08
    åİĭåĻ¨
    0.08
    ively
    0.08
    /de
    0.08
    หย
    0.08
    Activations Density 0.038%

    No Known Activations