© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22631
    Prev
    Next
    INDEX
    Explanations

    sexually transmitted diseases or infections

    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
    Negative Logits
    让ä¸ĸçķĮ
    -0.07
     Principle
    -0.06
    ugno
    -0.06
    äºİå¿ĥ
    -0.06
    etit
    -0.06
    æľºç»Ħ
    -0.06
    fall
    -0.06
     principle
    -0.06
    enge
    -0.06
    åħ¨çIJĥæľĢ大çļĦ
    -0.05
    POSITIVE LOGITS
    ubin
    0.06
    交æīĢ
    0.06
    é¢ľ
    0.05
     div
    0.05
     ord
    0.05
     adm
    0.05
    åºķæĿ¿
    0.05
    eof
    0.05
     Bed
    0.05
    å³
    0.05
    Activations Density 0.005%

    No Known Activations