© 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. 48075
    Prev
    Next
    INDEX
    Explanations

    difference or gradient

    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
    Jar
    -0.07
    姿
    -0.07
     dessen
    -0.06
    azy
    -0.06
    ä¸įåIJĮç¨ĭ度çļĦ
    -0.06
    kir
    -0.06
    ERM
    -0.06
    eles
    -0.06
    空å¿ĥ
    -0.06
    满满çļĦ
    -0.06
    POSITIVE LOGITS
    æĤ¬æ®Ĭ
    0.12
     between
    0.12
     междÑĥ
    0.10
    between
    0.10
     Between
    0.10
     بÙĬÙĨ
    0.09
    ระหวà¹Īาà¸ĩ
    0.09
     giữa
    0.09
     zwischen
    0.09
     mellan
    0.09
    Activations Density 0.023%

    No Known Activations