© 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. 25878
    Prev
    Next
    INDEX
    Explanations

    universitario Hopkins Children's Center State University

    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
     disper
    -0.07
    æĬ¢åħĪ
    -0.07
    饥
    -0.07
    cker
    -0.07
    coli
    -0.07
    让æĤ¨çļĦ
    -0.07
    é¢
    -0.07
    æģº
    -0.07
    á»iji
    -0.06
    ÑĦÑĥ
    -0.06
    POSITIVE LOGITS
    ä¹ĭåıĪ
    0.08
    acking
    0.07
    Withdraw
    0.07
     Respons
    0.07
    æ¶Īæģ¯
    0.07
    æĹłéĻħ
    0.07
    ×ŀ×Ļ×Ŀ
    0.07
    lada
    0.06
     respons
    0.06
    å®Ĺ
    0.06
    Activations Density 0.002%

    No Known Activations