© 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. 10417
    Prev
    Next
    INDEX
    Explanations

    acetabular component insertion

    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
    太太
    -0.08
    夫人
    -0.08
     hers
    -0.08
    åIJij她
    -0.08
    icha
    -0.08
    تÙĩا
    -0.07
    воÑĢ
    -0.07
    éĹ®å¥¹
    -0.07
    çĶŁæ°´
    -0.07
    иÑħ
    -0.07
    POSITIVE LOGITS
    å«ģç»Ļ
    0.09
    ä¸İ被åijĬ
    0.09
    editary
    0.08
    åIJij被åijĬ
    0.08
    åĴĮæī§è¡Į
    0.08
    ulas
    0.08
    èĢĮä»ĸ
    0.07
    åĩºå«ģ
    0.07
    esu
    0.07
     Gare
    0.07
    Activations Density 0.822%

    No Known Activations