© 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. 46011
    Prev
    Next
    INDEX
    Explanations

    function f"

    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¸įæĺİ
    -0.07
    ilih
    -0.07
    åįķ纯
    -0.06
    .unwrap
    -0.06
    ĵĴ
    -0.06
    -many
    -0.06
    å±ħå¤ļ
    -0.06
    ละ
    -0.06
    åİ
    -0.06
    ResourceId
    -0.06
    POSITIVE LOGITS
    åı²ä¸ĬçļĦ
    0.08
    ฯ
    0.08
    .cgi
    0.07
     rewritten
    0.07
    ä¸Ĭè¯ģ
    0.07
     Alte
    0.07
    artal
    0.07
    éĩįåĨĻ
    0.07
    æld
    0.07
    åľ¨è¿ĻäºĽ
    0.06
    Activations Density 0.003%

    No Known Activations