© 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. 16684
    Prev
    Next
    INDEX
    Explanations

    detail and imaging

    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
     perpet
    -0.07
    undy
    -0.07
     either
    -0.07
    aped
    -0.07
    jah
    -0.06
    _successful
    -0.06
    deen
    -0.06
    illah
    -0.06
    è¦ģä¹Ī
    -0.06
     gradually
    -0.06
    POSITIVE LOGITS
    ç²¾ç»Ĩ
    0.11
     بدÙĤØ©
    0.10
    精确
    0.10
    ç»Ĩå¾®
    0.09
    详ç»Ĩ
    0.09
    詳細
    0.09
     detail
    0.09
     detailed
    0.08
    ç»Ĩèĩ´
    0.08
    çļĦ详ç»Ĩ
    0.08
    Activations Density 0.388%

    No Known Activations