© 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. 17427
    Prev
    Next
    INDEX
    Explanations

    spanning trees and connectivity

    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
     Sands
    -0.07
    is
    -0.07
    åīįåı°
    -0.06
    æ¾Ī
    -0.06
    ãĤµãĥ³ãĥī
    -0.06
     worn
    -0.06
     ноÑģиÑĤ
    -0.06
    é¢ĵ
    -0.06
    åıĺæĢģ
    -0.06
    代人
    -0.06
    POSITIVE LOGITS
    è¿ŀæİ¥
    0.09
     spanning
    0.09
    .bridge
    0.09
    è¿ŀéĢļ
    0.08
     connectivity
    0.08
    /connect
    0.08
    éĢ£æİ¥
    0.08
    çļĦè¿ŀæİ¥
    0.08
     bridges
    0.08
    æįĨç»ij
    0.08
    Activations Density 0.009%

    No Known Activations