© 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. 13188
    Prev
    Next
    INDEX
    Explanations

    elasticity, stiffness, compliance

    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
    гей
    -0.09
     burned
    -0.08
    arkt
    -0.08
    acruz
    -0.08
    enaire
    -0.08
    .wind
    -0.08
    çģ¼
    -0.08
    δÏģο
    -0.08
     sidel
    -0.08
    TRL
    -0.08
    POSITIVE LOGITS
    å¼¹æĢ§
    0.12
     elastic
    0.10
     elasticity
    0.10
     compress
    0.09
     volume
    0.09
     deformation
    0.09
    elastic
    0.09
     Elastic
    0.09
     deform
    0.08
    å¼¹
    0.08
    Activations Density 0.008%

    No Known Activations