© 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. 19494
    Prev
    Next
    INDEX
    Explanations

    sexual harassment and misconduct

    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
    éĢŁåº¦ä¸İ
    -0.06
    anti
    -0.06
    urf
    -0.06
    วà¸Ķ
    -0.06
    æķ£åİ»
    -0.06
    ayat
    -0.06
    缸æĢĿ
    -0.06
    å®£ä¼łåįķ
    -0.06
    æĿIJæĸĻä¸İ
    -0.06
    建议使çĶ¨
    -0.06
    POSITIVE LOGITS
    件
    0.06
    iak
    0.05
    人身
    0.05
    æ±Ĥ
    0.05
     focusing
    0.05
     semiclass
    0.05
     foc
    0.05
    çĻĮ
    0.05
     univers
    0.05
    害
    0.05
    Activations Density 0.004%

    No Known Activations