© 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. 8798
    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
    гÑĢе
    -0.07
    è¾IJ
    -0.07
    ãģ¨æĢĿãĤıãĤĮãĤĭ
    -0.06
    æľºç»Ħ
    -0.06
    æĶ¶æĶ¯
    -0.06
     adul
    -0.06
    é¦ĸ缸
    -0.06
    æĶ¯è¡Į
    -0.06
    λάÏĩ
    -0.06
    гÑĢи
    -0.06
    POSITIVE LOGITS
    esak
    0.08
    iksa
    0.08
    æĹłä¸Ĭ
    0.07
    æ¡ĪçļĦ
    0.07
    æĺ¥æ±Ł
    0.07
    eble
    0.07
    ibble
    0.07
    ayat
    0.07
     CONTR
    0.07
    妨
    0.07
    Activations Density 0.000%

    No Known Activations