© 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. 19691
    Prev
    Next
    INDEX
    Explanations

    numbers or codes in parentheses

    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
    è¿Ļ两ç§į
    -0.10
    åıĮåıĮ
    -0.09
    è¿Ļ两个
    -0.09
    è¿Ļ两ä½į
    -0.09
    éĢĻåħ©
    -0.09
    è¿Ļ两
    -0.09
     ÙħÙĨÙĩÙħا
    -0.09
     beide
    -0.08
    è¿Ļ两款
    -0.08
    ãģ©ãģ¡ãĤīãĤĤ
    -0.08
    POSITIVE LOGITS
    ä¸īæĸ¹
    0.09
    è¿Ļä¸ī
    0.08
    ä¸īæĶ¯
    0.08
    è¿Ļä¸ī个
    0.08
    ä¸īèĢħ
    0.08
    åīįä¸ī
    0.07
    three
    0.07
     tro
    0.07
     trio
    0.07
    ä¸ĭäºĨ
    0.07
    Activations Density 0.177%

    No Known Activations