© 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. 945
    Prev
    Next
    INDEX
    Explanations

    different statuses and variations

    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
    alah
    -0.07
    é«ĺé«ĺ
    -0.07
    andal
    -0.07
    广大
    -0.07
    erven
    -0.07
    çĤ¹ä»Ģä¹Ī
    -0.06
    æĹłéĺ»
    -0.06
    ä¸įåĬ¨æijĩ
    -0.06
    enta
    -0.06
    为åİŁæĸĻ
    -0.06
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.22
     different
    0.20
    ä¸įåIJĮ
    0.18
    ä¹Łä¸įåIJĮ
    0.18
    different
    0.18
     differs
    0.18
    ä¸įä¸Ģæł·
    0.18
     differing
    0.18
     differently
    0.18
    çļĦä¸įåIJĮ
    0.17
    Activations Density 0.148%

    No Known Activations