© 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. 22099
    Prev
    Next
    INDEX
    Explanations

    future careers and education

    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
    èĭ±æĸĩåŃĹ
    -0.07
    alni
    -0.06
    erd
    -0.06
     à®¨à®Ł
    -0.06
    æľīä¸Ģ份
    -0.06
     existi
    -0.06
    æľīä¸Ģçķª
    -0.06
     ê²ĥìĿ´ëĿ¼ëĬĶ
    -0.06
    æľ«ä¸ĸ
    -0.06
    ä¸įè°ĥ
    -0.06
    POSITIVE LOGITS
    天涯
    0.05
     inherent
    0.05
    ience
    0.05
    éľĢè¦ģæĪij们
    0.05
     instantaneous
    0.05
     pre
    0.05
     Stage
    0.05
    utting
    0.05
    篷
    0.05
    ç¥ŀåĻ¨
    0.05
    Activations Density 0.017%

    No Known Activations