© 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. 14058
    Prev
    Next
    INDEX
    Explanations

    issues with non-English characters

    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
    ä¹ĺæľº
    -0.09
    ãģĸãģ¾
    -0.08
    empre
    -0.08
    ãģĹãģıãģ¯
    -0.08
    pras
    -0.08
    ä¸į误
    -0.07
    çľĭå¾Ĺ
    -0.07
     atrac
    -0.07
     unheard
    -0.07
     créd
    -0.07
    POSITIVE LOGITS
    æĢİä¹ĪåĬŀåij¢
    0.09
    å¿ħé¡»è¿Ľè¡Į
    0.08
    æĢİä¹ĪåĬŀ
    0.07
    åĽłä¸ºæĺ¯
    0.07
    æīĢ以éľĢè¦ģ
    0.07
    ä¸Ģå¼Ģå§ĭ
    0.07
     ideal
    0.07
     neither
    0.07
    æĢİ麼辦
    0.07
     ведÑĮ
    0.07
    Activations Density 0.195%

    No Known Activations