© 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. 31837
    Prev
    Next
    INDEX
    Explanations

    macos, code elements, assignments

    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
    städ
    -0.08
     ...\
    -0.07
    ä¸Ģåİ»
    -0.07
    %!
    -0.07
    :...
    -0.07
    è»
    -0.07
    认å®ļçļĦ
    -0.07
    oust
    -0.07
    æѤæŶçļĦ
    -0.06
    taan
    -0.06
    POSITIVE LOGITS
    ļ
    0.08
    ¨
    0.08
     Schon
    0.07
    Ī
    0.06
    HT
    0.06
    ẩn
    0.06
    «
    0.06
     respectively
    0.06
    ļĮ
    0.06
     phosphate
    0.06
    Activations Density 0.727%

    No Known Activations