© 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. 32045
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    æħ§èģª
    -0.08
    à¸Łà¹īา
    -0.07
    çļĦä¸Ģå®ļ
    -0.07
    /configuration
    -0.07
    /calendar
    -0.07
    èĢĥãģĪãĤĭ
    -0.07
    -0.07
    CAA
    -0.07
    drawable
    -0.07
    /entity
    -0.07
    POSITIVE LOGITS
    å¯
    0.07
    åºĨ
    0.06
    olders
    0.06
    转载请注æĺİ
    0.06
    _Pin
    0.06
     fotovolta
    0.06
    ompiler
    0.06
     featured
    0.06
    -pdf
    0.06
     appe
    0.06
    Activations Density 0.006%

    No Known Activations