© 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. 62849
    Prev
    Next
    INDEX
    Explanations

    content series/excerpts/interviews

    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
    igu
    -0.07
    ç½¢
    -0.06
    æīĢå±ŀè¡Įä¸ļ
    -0.06
     sufficiently
    -0.06
    æ³ķåĪĻ
    -0.06
     negative
    -0.06
     aggressive
    -0.06
     overshadow
    -0.06
    æīĢæĢĿ
    -0.06
    ä¹ĭæīĢ以
    -0.06
    POSITIVE LOGITS
    çļĦæľĭåıĭåı¯ä»¥
    0.08
     »»
    0.08
    ãģĵãģ¡ãĤīãĤĤ
    0.07
    pdf
    0.07
     anytime
    0.07
     Patrimonio
    0.07
    includes
    0.07
     Schuld
    0.07
     fascinating
    0.07
    å¸®ä½ł
    0.07
    Activations Density 0.764%

    No Known Activations