© 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. 3458
    Prev
    Next
    INDEX
    Explanations

    multiplication or cross symbol

    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
    تع
    -0.08
    lega
    -0.08
    utton
    -0.08
    ت
    -0.08
    ilyn
    -0.08
    ä¸ĭæĸ¹äºĮç»´çłģ
    -0.08
    家ä¼Ļ
    -0.08
    velope
    -0.08
    pite
    -0.08
    jenigen
    -0.08
    POSITIVE LOGITS
    她表示
    0.08
    ัà¸ĩ
    0.08
    Ñı
    0.08
    è¿Ļ便æĺ¯
    0.08
    o
    0.08
    iels
    0.07
    ëį°ìļĶ
    0.07
    Ùĩ
    0.07
    perience
    0.07
    iha
    0.07
    Activations Density 0.007%

    No Known Activations