© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39393
    Prev
    Next
    INDEX
    Explanations

    smooth, continuously differentiable

    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
    ä¸į大çļĦ
    -0.09
    èĵĿåŃĹ
    -0.08
    ysis
    -0.08
    itung
    -0.08
    aik
    -0.08
    å¦ĩ女èĬĤ
    -0.08
    áĥªáĥĺ
    -0.08
    amet
    -0.08
    ä¸İæŶ
    -0.08
    缩水
    -0.08
    POSITIVE LOGITS
     smooth
    0.07
     Smooth
    0.06
    smooth
    0.06
    级以ä¸Ĭ
    0.06
    å·¡åĽŀ
    0.06
    ä¸Ķåħ·æľī
    0.06
    Smooth
    0.06
    inker
    0.06
    è£ı
    0.06
     Tul
    0.06
    Activations Density 0.007%

    No Known Activations