© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17756
    Prev
    Next
    INDEX
    Explanations

    regression and scatter plots

    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
    ä¸īçĶ²
    -0.08
    mails
    -0.07
    piring
    -0.07
     Schau
    -0.07
     playable
    -0.07
    綿
    -0.07
     resolutions
    -0.07
     vacuum
    -0.07
    perms
    -0.07
     Elli
    -0.07
    POSITIVE LOGITS
    æĭŁåIJĪ
    0.12
     fitted
    0.11
    模åŀĭçļĦ
    0.10
    模åŀĭ
    0.10
    predict
    0.09
     forecasting
    0.09
     regression
    0.09
     fit
    0.09
     Regression
    0.09
     regres
    0.09
    Activations Density 0.024%

    No Known Activations