© 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. 43213
    Prev
    Next
    INDEX
    Explanations

    termination or negative actions

    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
    ä¸īæĹ¥
    -0.09
    è¿Ļ两ä½į
    -0.08
    ä¸ĥæĹ¥
    -0.08
    äºĮåįģå¹´
    -0.08
    ä¸Ģè¨Ģ
    -0.08
    ä¸Ģ寸
    -0.07
    çĻ¾å²ģ
    -0.07
    ä¸īå¹´åĨħ
    -0.07
    ä¹Ŀå¹´
    -0.07
    ailed
    -0.07
    POSITIVE LOGITS
     fewer
    0.15
    èĭ¥å¹²
    0.13
    èĭ¥å¹²ä¸ª
    0.12
    å¤ļäºİ
    0.12
    å¤ļè¾¾
    0.12
    è¾ĥå¤ļçļĦ
    0.12
    å°ijäºİ
    0.11
    æĽ´å¤ļçļĦ
    0.11
     sejumlah
    0.11
     تعداد
    0.11
    Activations Density 0.400%

    No Known Activations