© 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. 65468
    Prev
    Next
    INDEX
    Explanations

    agglomerations and clustering

    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
    à¸ĭัà¸ģ
    -0.08
    å¤ļç§įå½¢å¼ı
    -0.08
    anmar
    -0.08
    ATTER
    -0.07
    yday
    -0.07
     Pha
    -0.07
    abwe
    -0.07
    ALAR
    -0.07
    .slim
    -0.07
    пÑĮ
    -0.07
    POSITIVE LOGITS
    åIJĪ并
    0.09
    /connect
    0.08
     merging
    0.08
     merges
    0.07
     hashing
    0.07
    merge
    0.07
    .union
    0.07
     merge
    0.07
     union
    0.07
     merger
    0.07
    Activations Density 0.002%

    No Known Activations