© 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. 29100
    Prev
    Next
    INDEX
    Explanations

    example listings

    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
    à¸ļาล
    -0.08
    ayan
    -0.08
    /cc
    -0.08
    æĢªä¸įå¾Ĺ
    -0.07
    .isSelected
    -0.07
    åĿıäºĭ
    -0.07
     orto
    -0.07
    ×ĵ×Ļ×Ŀ
    -0.07
    ReadWrite
    -0.07
    æ±Łæµ·
    -0.07
    POSITIVE LOGITS
    erm
    0.07
    ellem
    0.06
    hom
    0.06
     Lans
    0.06
    oma
    0.06
     Buckley
    0.06
    acha
    0.06
    (!
    0.06
     WITHOUT
    0.06
    ennes
    0.06
    Activations Density 0.002%

    No Known Activations