© 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. 10564
    Prev
    Next
    INDEX
    Explanations

    -webkit- CSS properties

    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
    _construct
    -0.06
    unge
    -0.06
    ense
    -0.06
    轻声
    -0.06
    ↵↵
    -0.06
    èĬį
    -0.06
    æĭĴ
    -0.06
    åĢ¼å¾Ĺ
    -0.06
     Set
    -0.06
    è£ħ饰设计
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.08
    yclic
    0.08
    AttributeName
    0.08
    orium
    0.08
    .spi
    0.08
    leine
    0.08
    ìĿ´ìĥģ
    0.08
    à¸Ļิà¹Īà¸ĩ
    0.08
     ÑĨикл
    0.08
    züg
    0.08
    Activations Density 0.001%

    No Known Activations