© 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. 48538
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    edel
    -0.09
    èĩ¼
    -0.08
    æĶ¶èĹıæľ¬ç«Ļ
    -0.08
     SarÃł
    -0.08
    å¿Ĺ
    -0.07
    ANDOM
    -0.07
    egel
    -0.07
    ä¹Łä¸įçŁ¥éģĵ
    -0.07
    è£ķ
    -0.07
    tret
    -0.07
    POSITIVE LOGITS
    æĮĩçļĦæĺ¯
    0.09
    æĺ¯æĮĩ
    0.08
    主è¦ģæĺ¯æĮĩ
    0.08
    æĺ¯ä»Ģä¹ĪæĦıæĢĿ
    0.07
    áĥĺáĥ¡
    0.07
     refers
    0.07
    åŃIJæĺ¯
    0.07
    ren
    0.06
    家æĺ¯
    0.06
    æĮĩçļĦ
    0.06
    Activations Density 0.000%

    No Known Activations