© 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. 32848
    Prev
    Next
    INDEX
    Explanations

    mutable data structures

    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
    对æѤä¸įæī¿æĭħä»»ä½ķ
    -0.08
    管æīĢ
    -0.07
    æĹ¥ä¸Ĭ
    -0.07
    iggins
    -0.07
    纷åijĪ
    -0.07
    æĸ¯åį¡
    -0.07
    haust
    -0.07
    天çĽĸ
    -0.07
    GenerationStrategy
    -0.07
    .KeyCode
    -0.07
    POSITIVE LOGITS
    ä¿®æĶ¹
    0.11
     modified
    0.10
     mutable
    0.09
    _modified
    0.09
    modify
    0.09
    æĶ¹
    0.09
     Modified
    0.09
    æĶ¹åĬ¨
    0.09
    æĶ¹äºĨ
    0.09
    ä¸įæĶ¹
    0.09
    Activations Density 0.161%

    No Known Activations