© 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. 25534
    Prev
    Next
    INDEX
    Explanations

    programming data types

    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
    ÅĽcie
    -0.07
    ciÄħż
    -0.07
    ungan
    -0.07
     Zaj
    -0.07
     Sá
    -0.07
    輩
    -0.07
    åĨįæİ¥
    -0.07
    หà¹Į
    -0.06
    allar
    -0.06
    hao
    -0.06
    POSITIVE LOGITS
    Ùħاس
    0.07
    临
    0.07
    èĶĵ
    0.07
    ucker
    0.06
    енÑĤов
    0.06
    à¹Ģà¸Ĭà¹Īà¸Ļà¸ģัà¸Ļ
    0.06
    äºĴ
    0.06
     ups
    0.06
    OMPI
    0.06
    onti
    0.06
    Activations Density 0.127%

    No Known Activations