© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17873
    Prev
    Next
    INDEX
    Explanations

    coding library imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adays
    -0.05
     khai
    -0.05
    人æĿ¥è¯´
    -0.05
     Salem
    -0.05
    \t
    -0.05
     bogus
    -0.05
    .exe
    -0.05
    j
    -0.05
    æľ¬ä¹¦
    -0.05
    æľ¬æĽ¸
    -0.05
    POSITIVE LOGITS
    از
    0.07
     nab
    0.07
    undu
    0.06
    (qu
    0.06
    ä¼ģä¸ļç»ıèIJ¥
    0.06
    æĻ®éĢļè¯Ŀ
    0.06
    anch
    0.06
    ảnh
    0.06
    -name
    0.05
    kees
    0.05
    Activations Density 0.013%

    No Known Activations