© 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. 41693
    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
    Ñĥнк
    -0.08
    åºı
    -0.08
    æIJħ
    -0.07
    ãĤīãģı
    -0.07
    عÙĪÙĨ
    -0.07
    _nth
    -0.06
    ynos
    -0.06
    ä½Ĩæĺ¯çĶ±äºİ
    -0.06
    lass
    -0.06
    еÑĩно
    -0.06
    POSITIVE LOGITS
    =}
    0.07
    ç»Ļä½łçļĦ
    0.07
    à¸Ļ
    0.07
    itag
    0.07
    æĸ°è¯¾
    0.06
    æ³ĵ
    0.06
    auer
    0.06
    ÏĢλα
    0.06
    áŀĽ
    0.06
    ilik
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.