© 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. 49070
    Prev
    Next
    INDEX
    Explanations

    (born [date])

    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
    缴æİ¥æĪĸ
    -0.07
    ãĥIJãĥĬ
    -0.07
    å·
    -0.07
    ãģ¾ãģ¾
    -0.07
    ä¸įèĥ½å®Įåħ¨
    -0.06
    ä¹Łå°±
    -0.06
    ëĭ¤ë©´
    -0.06
     tev
    -0.06
    tev
    -0.06
    ocale
    -0.06
    POSITIVE LOGITS
    ä¸įä¸Ģæł·çļĦ
    0.08
    ynt
    0.08
    elda
    0.07
    oley
    0.07
     Kül
    0.07
    adow
    0.07
    asel
    0.07
    enville
    0.07
     McKin
    0.07
    Ïĥμ
    0.07
    Activations Density 0.260%

    No Known Activations