© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20292
    Prev
    Next
    INDEX
    Explanations

    remote and flexible work arrangements

    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
    缮
    -0.06
    ŀ
    -0.05
    容éĩı
    -0.05
    .in
    -0.05
    ä¸Ģ票
    -0.05
    åºĶæĢ¥ç®¡çIJĨå±Ģ
    -0.05
     Emin
    -0.05
    åĮª
    -0.05
    ר×Ĺ
    -0.05
    esthesia
    -0.05
    POSITIVE LOGITS
    ä¼ģä¸ļåĴĮ
    0.07
    ιÏİ
    0.07
    ucin
    0.06
    fäl
    0.06
    ÏĮδ
    0.06
    ç§ĺ
    0.06
    Ahead
    0.06
    pike
    0.06
     experiment
    0.06
    ä¼ģä¸ļä¸Ń
    0.06
    Activations Density 0.005%

    No Known Activations