© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20662
    Prev
    Next
    INDEX
    Explanations

    carcinogen potential

    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
     soon
    -0.05
     dependent
    -0.05
    uwen
    -0.05
    à¸Ĥัà¸ļ
    -0.05
    æ¢Ń
    -0.05
    è¿ĩçļĦ
    -0.05
    ä¸įåħį
    -0.05
     Tir
    -0.05
     ruá»Ļt
    -0.05
     Lem
    -0.05
    POSITIVE LOGITS
    ÑĢалÑĮ
    0.06
    inya
    0.06
    vera
    0.05
    ç¥ł
    0.05
    iem
    0.05
    inge
    0.05
    éĩijæĽ²
    0.05
    eka
    0.05
    tec
    0.05
    altar
    0.05
    Activations Density 0.003%

    No Known Activations