© 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. 63707
    Prev
    Next
    INDEX
    Explanations

    small or tiny measurements

    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
    çļĦ大åŀĭ
    -0.09
    å·¨åŀĭ
    -0.08
     mega
    -0.08
    大åŀĭçļĦ
    -0.08
    大åŀĭ
    -0.07
    巨大
    -0.07
    unc
    -0.07
    Large
    -0.07
     large
    -0.07
    çĿ£
    -0.07
    POSITIVE LOGITS
    å°ıå·§
    0.12
     tiny
    0.12
    Tiny
    0.12
    å¾Īå°ıçļĦ
    0.11
     pequenas
    0.11
    å¾Īå°ı
    0.10
    tiny
    0.10
     Tiny
    0.10
    è¿·ä½ł
    0.10
    èĻ½å°ı
    0.10
    Activations Density 0.382%

    No Known Activations