© 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. 17721
    Prev
    Next
    INDEX
    Explanations

    character names or titles

    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
    æķ´å½¢
    -0.06
    è£Ķ
    -0.05
    äter
    -0.05
    çļĦ交æĺĵ
    -0.05
    ztat
    -0.05
    ämä
    -0.05
    enge
    -0.05
     rex
    -0.05
    ãĥ¼ãĥŀ
    -0.05
    uci
    -0.05
    POSITIVE LOGITS
     butter
    0.06
    æģĴ
    0.06
    éĻIJ
    0.06
    è°ĥåĴĮ
    0.06
    ä½ľä¸ºä¸Ģ家
    0.05
    orth
    0.05
     discontinued
    0.05
    utherford
    0.05
     slu
    0.05
    稳å®ļ
    0.05
    Activations Density 0.001%

    No Known Activations