© 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. 21022
    Prev
    Next
    INDEX
    Explanations

    present invention

    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
     Ramirez
    -0.08
    -Mart
    -0.08
    ľ
    -0.07
    -gap
    -0.07
    å¼ı设计
    -0.07
    å¾·åįİ
    -0.06
     Gap
    -0.06
    å°±æĭ¿
    -0.06
    éĹ´éļĻ
    -0.06
    åıĸäºĨ
    -0.06
    POSITIVE LOGITS
    urf
    0.08
    ogr
    0.07
    Õ²
    0.07
    rock
    0.07
    ross
    0.07
    oplevel
    0.07
     manh
    0.07
    ÙĪاج
    0.07
    abble
    0.07
    зок
    0.07
    Activations Density 0.013%

    No Known Activations