© 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. 55648
    Prev
    Next
    INDEX
    Explanations

    threshold value

    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
    è¨
    -0.08
    é¦Ļèįī
    -0.07
    代
    -0.07
    ¾¸
    -0.07
    .onCreate
    -0.07
     consenting
    -0.07
    arella
    -0.07
    _stdio
    -0.07
    жели
    -0.06
    _tensors
    -0.06
    POSITIVE LOGITS
    æľī太å¤ļ
    0.08
    ç»Ŀ
    0.07
    太强
    0.07
     пÑĢевÑĭ
    0.07
     capability
    0.07
     too
    0.07
     allowable
    0.06
    ãĤ¤ãĤ¯
    0.06
     guarantee
    0.06
    aky
    0.06
    Activations Density 0.021%

    No Known Activations