© 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. 26648
    Prev
    Next
    INDEX
    Explanations

    class __init__ method

    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
    PropTypes
    -0.08
    wski
    -0.08
    ISE
    -0.08
    wares
    -0.08
    سÙĩ
    -0.08
    ÎŃÏģγ
    -0.08
    меÑĢа
    -0.07
    inos
    -0.07
    ä¹ĭä¸į
    -0.07
    åŀĭä¼ģä¸ļ
    -0.07
    POSITIVE LOGITS
    0.06
    lass
    0.06
    çļ®
    0.06
    ili
    0.06
    0.06
    <tool_response>
    0.06
    ä¸Ĭ
    0.06
    ango
    0.06
    itial
    0.06
    ua
    0.06
    Activations Density 0.008%

    No Known Activations