© 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. 47369
    Prev
    Next
    INDEX
    Explanations

    integrals and sums

    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
    idon
    -0.07
    äºijæµ®
    -0.06
    ä¸īæ¸ħ
    -0.06
    è¾ĥå°ij
    -0.06
    ä¸įåıĤä¸İ
    -0.06
    èĩªå·±æľī
    -0.06
    Ĥ¹
    -0.06
     Padr
    -0.06
    hud
    -0.06
    æĸ¹éĿ¢çļĦ
    -0.06
    POSITIVE LOGITS
    беÑĢе
    0.08
    Ń
    0.08
    çī©çIJĨ
    0.08
    çī©
    0.07
     boyunca
    0.07
    .allowed
    0.07
    éĩijæĸ¯
    0.07
    ndl
    0.07
    tol
    0.07
    çī©åĴĮ
    0.07
    Activations Density 0.003%

    No Known Activations