© 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. 27047
    Prev
    Next
    INDEX
    Explanations

    Impact/Inc prefixes

    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
    åģ¥
    -0.07
    ism
    -0.07
    lü
    -0.06
    缸æī£
    -0.06
    èĭ±ä¿Ĭ
    -0.06
    ahi
    -0.06
    ÙĨدÙĨ
    -0.06
    ηγ
    -0.06
    ians
    -0.06
    tep
    -0.06
    POSITIVE LOGITS
    engel
    0.08
     নিয়à§ĩ
    0.08
    éī´
    0.07
    çļĦä¸įèī¯
    0.07
    èµ´
    0.07
    ظة
    0.07
    å°»
    0.07
    æĹłéĿŀ
    0.07
    utsch
    0.07
    å¼łåı£
    0.07
    Activations Density 0.001%

    No Known Activations