© 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. 18160
    Prev
    Next
    INDEX
    Explanations

    any type or general

    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
    hiri
    -0.06
    hes
    -0.06
    åIJĦç§įåIJĦæł·
    -0.06
    íĽ¨
    -0.06
    æķĻèĤ²èĢĥè¯ķ
    -0.06
    ä¸Ĭä¼łèĢħ
    -0.06
    꽤
    -0.06
    个åĽŀçŃĶ
    -0.06
    ÑĨионе
    -0.06
    PIO
    -0.05
    POSITIVE LOGITS
    æĸĩåĮĸçŁ¥è¯Ĩ
    0.06
    åĴĮ解
    0.05
    hop
    0.05
    olt
    0.05
    TL
    0.05
    éĺµåľ°
    0.05
    r
    0.05
    ac
    0.05
    nde
    0.05
     Nus
    0.05
    Activations Density 0.001%

    No Known Activations