© 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. 27679
    Prev
    Next
    INDEX
    Explanations

    purpose and features

    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
    彤
    -0.08
    <|box_end|>
    -0.08
    åĪļä¸Ģ
    -0.08
    æ
    -0.07
    istri
    -0.07
    ately
    -0.07
    <tool_response>
    -0.07
    izzi
    -0.07
    enty
    -0.07
    èļ
    -0.07
    POSITIVE LOGITS
    ä¸Ĭå½ĵ
    0.07
    agher
    0.07
    HELP
    0.06
    vo
    0.06
    ä¸ĬåĬł
    0.06
    ä¹ŁæĪIJäºĨ
    0.06
    è¸ıå®ŀ
    0.06
    à¸ļุรี
    0.06
     Digit
    0.06
    æĹłè¨Ģ
    0.06
    Activations Density 0.001%

    No Known Activations