© 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. 16610
    Prev
    Next
    INDEX
    Explanations

    singular, plural, and gender forms

    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
    baugh
    -0.09
    alani
    -0.08
    oze
    -0.08
    bery
    -0.07
    weg
    -0.07
    ologen
    -0.07
    erah
    -0.07
    chie
    -0.07
    áticos
    -0.07
     Executor
    -0.07
    POSITIVE LOGITS
     singular
    0.07
    çıĬçıĬ
    0.07
     noun
    0.07
    ר×ķ
    0.06
    ä¾ĭåı¥
    0.06
    สะ
    0.06
    inded
    0.06
     object
    0.06
    ileo
    0.06
     plural
    0.06
    Activations Density 0.014%

    No Known Activations