© 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. 18284
    Prev
    Next
    INDEX
    Explanations

    plasticity, engineering, properties, software, behaviors, therapy, cells, operations

    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
    ç³»ç»ŁåĴĮ
    -0.07
    /system
    -0.07
    ç³»ç»Łä¸İ
    -0.07
    лок
    -0.06
    /System
    -0.06
    å¼±çĶµ
    -0.06
    çĶ¨äºº
    -0.06
    ç³»ç»ŁåıĬ
    -0.05
     prof
    -0.05
    ajak
    -0.05
    POSITIVE LOGITS
    诸å¦Ĥ
    0.15
     operations
    0.10
    åĽĽç§į
    0.10
    äºĶç§į
    0.10
    åħŃç§į
    0.10
    Operations
    0.09
    åĮħæĭ¬
    0.09
     Operations
    0.09
     meliputi
    0.09
    operations
    0.09
    Activations Density 1.031%

    No Known Activations