© 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. 45443
    Prev
    Next
    INDEX
    Explanations

    viscoelasticity, friction, stiffness, compressibility

    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
    rary
    -0.07
    æĶ¿çŃĸæĢ§
    -0.07
    ĥģ
    -0.07
    dert
    -0.07
    .rdf
    -0.07
    urette
    -0.07
    shaw
    -0.07
    llib
    -0.07
    sker
    -0.07
    oproject
    -0.07
    POSITIVE LOGITS
    é£İä¿Ĺ
    0.07
    ort
    0.07
    æĬ
    0.07
    ayer
    0.07
     compress
    0.06
     unin
    0.06
    orts
    0.06
    speed
    0.06
    å¯Ĩ
    0.06
    éĺĶ
    0.06
    Activations Density 0.002%

    No Known Activations