© 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. 16391
    Prev
    Next
    INDEX
    Explanations

    Augustine and Benedict

    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
    æĮºçĽ´
    -0.08
    å±¥è¡ĮåIJĪåIJĮ
    -0.07
     toJSON
    -0.07
     kling
    -0.07
     Nepal
    -0.07
    éĶ£
    -0.07
    æľīäºĽäºĭ
    -0.07
    ielo
    -0.07
    ureau
    -0.07
    ãģĵãģł
    -0.07
    POSITIVE LOGITS
    åľ£å¥³
    0.07
    pty
    0.07
    qli
    0.07
    retched
    0.07
     Augustine
    0.07
    beau
    0.06
    èİİ
    0.06
    ·
    0.06
     theolog
    0.06
     Escr
    0.06
    Activations Density 0.013%

    No Known Activations