© 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. 13973
    Prev
    Next
    INDEX
    Explanations

    determined by

    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
    ISTI
    -0.07
    MISSION
    -0.07
    -src
    -0.07
    istol
    -0.06
    riend
    -0.06
     оÑģнов
    -0.06
    ç¥ī
    -0.06
    <>
    -0.06
     lomb
    -0.06
    KEEP
    -0.06
    POSITIVE LOGITS
    uche
    0.08
    udas
    0.08
    èĮĥåĨ°åĨ°
    0.08
    ä¸įæ²»
    0.07
    tront
    0.07
    usch
    0.07
    液æĻ¶å±ı
    0.07
    è°ĵä¹ĭ
    0.07
    (er
    0.07
    ulas
    0.07
    Activations Density 0.365%

    No Known Activations