© 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. 20774
    Prev
    Next
    INDEX
    Explanations

    book or article sections

    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
    åģļäºĽ
    -0.09
    éĥ½æĺ¯ä¸ĢäºĽ
    -0.08
    对éĤ£äºĽ
    -0.08
    eien
    -0.08
    对äºİä¸ĢäºĽ
    -0.07
    åIJĦå¼ı
    -0.07
    ouched
    -0.07
    denes
    -0.07
    æľī太å¤ļ
    -0.07
    åĩłå®¶
    -0.07
    POSITIVE LOGITS
     appunto
    0.09
     ÑģобÑģÑĤвенно
    0.08
    åIJĮåIJį
    0.08
    ãģ¨ãģĹãģ¦ãģ®
    0.08
     version
    0.07
    _VERSION
    0.07
     tersendiri
    0.07
    念
    0.07
    asen
    0.07
    Version
    0.07
    Activations Density 0.603%

    No Known Activations