© 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. 8390
    Prev
    Next
    INDEX
    Explanations

    election year and event

    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
    天ä¹ĭ
    -0.08
    æľĪ以æĿ¥
    -0.07
    eck
    -0.07
    óp
    -0.07
    ä½įç½®åĴĮ
    -0.07
    thr
    -0.07
    çĪ½çļĦ
    -0.07
    ãĥ©ãģ®
    -0.07
    åĬĽåĴĮ
    -0.07
    å¹´ãģ¯
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.11
    çīĪ
    0.08
    æĹ¶æľŁ
    0.07
    <|box_end|>
    0.07
    rant
    0.07
    å¤į
    0.07
    áŁĭ
    0.07
    bach
    0.07
    夫æĸ¯åŁº
    0.07
    stoffe
    0.07
    Activations Density 0.015%

    No Known Activations