© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11884
    Prev
    Next
    INDEX
    Explanations

    explaining definitions

    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
    lee
    -0.09
    endor
    -0.08
    hofer
    -0.07
    encia
    -0.07
    elden
    -0.07
    ivre
    -0.07
    terra
    -0.07
    eer
    -0.07
    OLON
    -0.07
    家访
    -0.07
    POSITIVE LOGITS
    人æĪĸ
    0.08
    ä¸Ģç§į
    0.08
    ä»Ģä¹ĪæĦıæĢĿ
    0.07
    çļĦäºĭçī©
    0.07
    å¾Īå¤ļä¸ľè¥¿
    0.07
    缸å½ĵäºİ
    0.07
    çļĦæĦıæĢĿ
    0.07
    ikan
    0.07
     literally
    0.07
     shorthand
    0.07
    Activations Density 0.041%

    No Known Activations