© 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. 7959
    Prev
    Next
    INDEX
    Explanations

    regression and statistical modeling

    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
    fuse
    -0.08
     extr
    -0.07
    ÐĴС
    -0.07
     Brilliant
    -0.07
    大éĩı
    -0.07
    åķĨçĶ¨
    -0.07
    htm
    -0.07
    æĨ¨
    -0.07
    ¾
    -0.06
    utow
    -0.06
    POSITIVE LOGITS
    å¾Ĺèµ·
    0.08
     fitted
    0.08
     conditional
    0.08
    åĪ»çĶ»
    0.08
     Lik
    0.07
     modeled
    0.07
    conditional
    0.07
    ×ŀ×ķ×ĵ
    0.07
    OLS
    0.07
     regression
    0.07
    Activations Density 0.018%

    No Known Activations