© 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. 2301
    Prev
    Next
    INDEX
    Explanations

    describes or shows how

    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
    ä¹Łéļıä¹ĭ
    -0.06
    以ä¸ĭåĩłç§į
    -0.06
    одо
    -0.06
    erdale
    -0.06
    åľ¨ä»ĬåIJİçļĦ
    -0.06
    æĮļ
    -0.06
     préal
    -0.06
    undy
    -0.06
     instead
    -0.06
    ead
    -0.05
    POSITIVE LOGITS
    论
    0.08
    讨论äºĨ
    0.08
    aggio
    0.08
    åIJĮä¸Ĭ
    0.08
    .ToArray
    0.07
    úr
    0.07
     extensively
    0.07
    nil
    0.07
    ä½ľé£İ
    0.07
    ç¬ĶåIJį
    0.07
    Activations Density 0.038%

    No Known Activations