© 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. 49625
    Prev
    Next
    INDEX
    Explanations

    joint admission board

    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
    rett
    -0.08
    åįİåķĨ
    -0.07
    åĭģ
    -0.07
    çıŃéĩĮ
    -0.06
     {}\
    -0.06
    atar
    -0.06
    åĬ²åĦ¿
    -0.06
    ÑĨов
    -0.06
    dom
    -0.06
    finder
    -0.06
    POSITIVE LOGITS
    LER
    0.08
    ¬
    0.08
    бÑı
    0.08
    ctest
    0.07
    گاÙĨ
    0.07
    erville
    0.07
    oku
    0.07
    egov
    0.07
    ield
    0.07
    èĩªè¨Ģ
    0.07
    Activations Density 0.021%

    No Known Activations