© 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. 9370
    Prev
    Next
    INDEX
    Explanations

    participle endings or suffixes

    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
    让广大
    -0.07
    伯çĪµ
    -0.06
     aby
    -0.06
    åĴĮåķĨä¸ļ
    -0.06
    pth
    -0.06
    ssize
    -0.06
    以åıĬåIJĦç§į
    -0.06
    çļĦç»ıæµİ
    -0.06
    gress
    -0.06
    ichick
    -0.06
    POSITIVE LOGITS
     previamente
    0.10
    èµ·æĿ¥çļĦ
    0.10
     préal
    0.09
    åģļåĩºçļĦ
    0.08
    äºĭåħĪ
    0.08
    åIJİçļĦ
    0.08
    ified
    0.08
    ä½ľåĩºçļĦ
    0.08
     appropriately
    0.07
    äºĨçļĦ
    0.07
    Activations Density 0.804%

    No Known Activations