© 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. 17265
    Prev
    Next
    INDEX
    Explanations

    Chinese and English medical/technical terms

    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
     vice
    -0.06
    æĺ¯è¢«
    -0.06
    代çłģå¦Ĥä¸ĭ
    -0.06
     outright
    -0.06
     اÙĦتس
    -0.06
    请ä¸İ
    -0.05
    éviter
    -0.05
    åı¯èĥ½è¢«
    -0.05
    uropean
    -0.05
    ä¼ļ被
    -0.05
    POSITIVE LOGITS
     üzere
    0.07
    itus
    0.07
    aten
    0.06
    ä¸ĵä¸ļä»İäºĭ
    0.06
    èĢĮ以
    0.06
    ä¸ĭå®ļ
    0.06
    ä¸ĭ
    0.06
    igin
    0.06
     Mercer
    0.05
    azit
    0.05
    Activations Density 0.027%

    No Known Activations