© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19696
    Prev
    Next
    INDEX
    Explanations

    extramarital affairs

    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
    vertise
    -0.07
    åŃĺåľ¨ä¸Ģå®ļçļĦ
    -0.06
    ovn
    -0.06
    è²¢
    -0.06
    éħįç½®æĸ¹éĿ¢
    -0.06
    anam
    -0.06
    .âĢ¢
    -0.06
    èĥĮæĻ¯åĴĮ
    -0.06
    æ´¾
    -0.06
    omp
    -0.06
    POSITIVE LOGITS
    uft
    0.06
    ç§ģæľį
    0.05
    å®Ī
    0.05
    idi
    0.05
    æľªçĦ¶
    0.05
     breaking
    0.05
     ur
    0.05
     prestig
    0.05
    ujuk
    0.05
    каза
    0.05
    Activations Density 0.003%

    No Known Activations