© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59902
    Prev
    Next
    INDEX
    Explanations

    shear stress, flow, force

    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
    Negative Logits
    ãģĦãĤĭ
    -0.08
    oded
    -0.08
    san
    -0.07
    ional
    -0.07
    yel
    -0.07
    icing
    -0.07
    ÙĬÙĪÙĨ
    -0.07
    ations
    -0.07
    cers
    -0.07
    à¸ģารà¸ĵà¹Į
    -0.07
    POSITIVE LOGITS
    ikov
    0.08
    less
    0.08
    گاÙĩ
    0.08
    lessness
    0.07
    หà¸Ļà¹īาà¸Ĺีà¹Ī
    0.07
    머ëĭĪ
    0.07
    blade
    0.07
    èļĵ
    0.07
    ISTORY
    0.07
    ween
    0.07
    Activations Density 0.019%

    No Known Activations