© 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. 27019
    Prev
    Next
    INDEX
    Explanations

    analyze

    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
    atric
    -0.09
    äºĨ
    -0.08
     ë¶Ī구íķĺê³ł
    -0.08
    ศà¸Ī
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    ëģĶ
    -0.08
    gether
    -0.07
    inspace
    -0.07
    åĴĮ
    -0.07
    uestion
    -0.07
    POSITIVE LOGITS
    ÑĮÑı
    0.10
    åĴĮ建议
    0.09
    åħ¥å¾®
    0.09
     readonly
    0.08
    å¾Ĺå¾Ī
    0.07
    nh
    0.07
    íĦ´
    0.07
    çļĦå°±æĺ¯
    0.07
    ÛĮÙĩ
    0.07
    æ¸ħæ¥ļ
    0.07
    Activations Density 0.001%

    No Known Activations