© 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. 31347
    Prev
    Next
    INDEX
    Explanations

    Meta Description

    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¸įè¾ŀ
    -0.07
    ä¸įå½Ĵ
    -0.06
    ç«ĻçļĦ
    -0.06
    heil
    -0.06
    å½Ĵ
    -0.06
    ç«Ļ
    -0.06
    ulah
    -0.06
    å¹³æĹ¥
    -0.06
     exactly
    -0.06
    ichi
    -0.06
    POSITIVE LOGITS
    engang
    0.08
    agara
    0.08
    èİĬ
    0.07
    ngen
    0.07
    ä¸Ģ串
    0.07
    toff
    0.07
    èįĺ
    0.07
    åºĦ
    0.07
    боле
    0.07
    ê¸Ģ
    0.07
    Activations Density 0.377%

    No Known Activations