© 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. 62673
    Prev
    Next
    INDEX
    Explanations

    package or class name suffixes

    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
    Ç
    -0.06
    ’
    -0.06
    artner
    -0.06
     âĢ¦
    -0.06
    Identifier
    -0.06
    '
    -0.06
    **
    -0.06
    pecified
    -0.05
    >
    -0.05
    ‘
    -0.05
    POSITIVE LOGITS
    ä»Ģä¹ĪæĦıæĢĿ
    0.08
    æİĴ忧
    0.08
    mind
    0.08
     sehar
    0.08
    æĪijæĺ¯ä¸Ģ个
    0.08
    GetY
    0.07
    GetX
    0.07
    ارض
    0.07
    ä¹ĭåŁİ
    0.07
    +)/
    0.07
    Activations Density 0.310%

    No Known Activations