© 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. 11076
    Prev
    Next
    INDEX
    Explanations

    Chmerkovskiy, Morrongiello, Lagomarsino, Colamonici

    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
    åħ¼æĢ»ç»ıçIJĨ
    -0.08
    chester
    -0.08
    ÙĦÙĪد
    -0.07
    à¹ģหà¹Īà¸ĩà¸Ĭาà¸ķิ
    -0.07
    .tbl
    -0.07
    athan
    -0.07
    天ä¹ĭ
    -0.07
    ï¼Ŀï¼Ŀï¼Ŀï¼Ŀ
    -0.07
    .writeHead
    -0.07
    chiere
    -0.07
    POSITIVE LOGITS
    cind
    0.07
    adie
    0.06
    полÑĮ
    0.06
    ·
    0.06
    åĿ
    0.06
    cil
    0.06
    èIJ½å®ŀ好
    0.06
    ...',
    0.06
    mue
    0.06
    teo
    0.06
    Activations Density 1.800%

    No Known Activations