© 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. 34449
    Prev
    Next
    INDEX
    Explanations

    approximations and convergence

    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
    ulut
    -0.09
    icult
    -0.09
    षà¥įà¤ł
    -0.08
    饱
    -0.08
    麦å½ĵ
    -0.08
    uide
    -0.07
    istr
    -0.07
    为转载
    -0.07
    çļĦä¸Ģé¢Ĺ
    -0.07
     perch
    -0.07
    POSITIVE LOGITS
     approximation
    0.10
    è¿ijä¼¼
    0.09
     approx
    0.08
     infinit
    0.08
    线æĢ§
    0.08
     derivatives
    0.08
    çļĦå¹³åĿĩ
    0.08
    lope
    0.08
     Approx
    0.08
     aprox
    0.08
    Activations Density 0.073%

    No Known Activations