© 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. 51678
    Prev
    Next
    INDEX
    Explanations

    increases complexity or cost

    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
    æĺ¥åįİ
    -0.08
    大èĥĨ
    -0.08
    太差
    -0.08
    ÃģP
    -0.07
    大æľī
    -0.07
     доле
    -0.07
     Pruitt
    -0.07
     Brigham
    -0.07
     пÑĢедваÑĢ
    -0.07
    ialis
    -0.07
    POSITIVE LOGITS
     complexity
    0.14
    é¢Ŀå¤ĸ
    0.12
    é¢Ŀå¤ĸçļĦ
    0.12
     Complexity
    0.12
     complic
    0.11
     extra
    0.11
    å¤įæĿĤ度
    0.11
     added
    0.10
    å¤įæĿĤæĢ§
    0.10
    extra
    0.10
    Activations Density 0.088%

    No Known Activations