© 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. 12133
    Prev
    Next
    INDEX
    Explanations

    regression models

    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
    ứng
    -0.07
    DirectoryName
    -0.07
    梱
    -0.06
    оваÑĤелÑĮ
    -0.06
    oval
    -0.06
    å¢
    -0.06
     ÑĩеловеÑĩ
    -0.06
    directories
    -0.06
    Ñģан
    -0.06
    æķ£èIJ½
    -0.06
    POSITIVE LOGITS
     models
    0.09
    æĭŁåIJĪ
    0.08
     model
    0.08
     regression
    0.08
    模åŀĭ
    0.08
     Models
    0.08
     fitted
    0.08
     incorporating
    0.08
     ÑĢег
    0.08
    模åŀĭçļĦ
    0.08
    Activations Density 0.068%

    No Known Activations