© 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. 4153
    Prev
    Next
    INDEX
    Explanations

    viscosity

    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
    ì°į
    -0.08
    ../../../
    -0.08
    داء
    -0.07
     xá»ī
    -0.07
    ücks
    -0.07
     luas
    -0.07
    åĴĮåIJĮäºĭ
    -0.07
    ãĤĵãģ³
    -0.07
     biet
    -0.07
    å¿ĥæĥĬ
    -0.07
    POSITIVE LOGITS
    ع
    0.09
    osity
    0.09
    новÑĮ
    0.09
    oodoo
    0.08
    cosity
    0.08
    度çļĦ
    0.08
    utti
    0.08
    poke
    0.07
    engeance
    0.07
    Ń
    0.07
    Activations Density 0.008%

    No Known Activations