© 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. 46471
    Prev
    Next
    INDEX
    Explanations

    Walk MS

    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
     {@
    -0.08
    ��
    -0.08
    æľ¬åĬŀæ³ķ
    -0.07
     именно
    -0.07
    ...",
    -0.07
     ÑıкобÑĭ
    -0.07
     gewesen
    -0.07
    çļĦéĤ£æł·
    -0.07
    æīį对
    -0.07
    éĥ½ä¸įä¸Ģæł·
    -0.06
    POSITIVE LOGITS
     inoltre
    0.10
    ç½ij讯
    0.10
    æĺ¯æĮĩåľ¨
    0.10
     tehát
    0.09
    ï½ľ
    0.09
    çłĶ究表æĺİ
    0.09
    æĺ¯ä¸Ģ个å¾Ī
    0.09
     bowiem
    0.09
    ”:
    0.09
     ï¼ļ
    0.08
    Activations Density 2.691%

    No Known Activations