© 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. 25628
    Prev
    Next
    INDEX
    Explanations

    echocardiography, Islam, biochemical, native

    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
    èĢĮéĿŀ
    -0.07
    èĢĮå¤į
    -0.07
    èĢĮä¸įæĺ¯
    -0.07
    å¼ģ
    -0.07
    èī²æĸij
    -0.07
     alike
    -0.07
     rather
    -0.06
    rather
    -0.06
    ä¸įä»ħä»ħæĺ¯
    -0.06
     plutôt
    -0.06
    POSITIVE LOGITS
    è¿Ļä¸īç§į
    0.08
    faat
    0.08
    ãģłãģijãģ¯
    0.08
    vall
    0.08
    åľ¨è¿ĻäºĽ
    0.07
    ä¸īèĢħ
    0.07
    /module
    0.07
    第ä¸īç§į
    0.07
    è¿Ļä¸ī个
    0.07
    é£İåĴĮ
    0.07
    Activations Density 0.707%

    No Known Activations