© 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. 18857
    Prev
    Next
    INDEX
    Explanations

    "In the year" or "In... "

    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
    ä¸ļ
    -0.06
    ortun
    -0.06
    ÑĢав
    -0.05
     frigor
    -0.05
    били
    -0.05
    ç»Ħç»ĩåĴĮ
    -0.05
     Ma
    -0.05
    çľī
    -0.05
     dang
    -0.05
    æ·±
    -0.05
    POSITIVE LOGITS
    èıľçļĦ
    0.06
    ank
    0.05
    ext
    0.05
    交éĢļèŃ¦å¯Ł
    0.05
    ä¿Ŀ驾
    0.05
     tres
    0.05
    compat
    0.05
    ietro
    0.05
    Extent
    0.05
    åıĬæĬĢæľ¯
    0.05
    Activations Density 0.009%

    No Known Activations