© 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. 30317
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formulas

    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
    Âł
    -0.07
    -0.07
    ↵
    -0.07
    ↵↵
    -0.06
     (
    -0.06
    .define
    -0.05
    ä¸įèĢĥèĻij
    -0.05
    `.
    -0.05
     N
    -0.05
    ileo
    -0.05
    POSITIVE LOGITS
     seques
    0.09
    æݧèĤ¡éĽĨåĽ¢
    0.08
    icto
    0.08
     übrigens
    0.08
    :params
    0.08
    öst
    0.08
     doss
    0.08
     наÑģе
    0.08
    å¹²äºĨ
    0.08
    太éĥİ
    0.08
    Activations Density 0.013%

    No Known Activations