© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15598
    Prev
    Next
    INDEX
    Explanations

    companies and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    éļį
    -0.19
    ä¸ĸ人
    -0.18
    èĢ½
    -0.17
    ãģ©ãģĵãĤį
    -0.17
    hunter
    -0.17
    åĮĹ京大åѦ
    -0.17
    å¶Ļ
    -0.17
    è¿Ķ乡
    -0.17
    /details
    -0.17
    ðŁĵĤ
    -0.17
    POSITIVE LOGITS
    ®
    0.27
    æݨåĩºçļĦ
    0.24
     Inc
    0.24
    âĵĩ
    0.24
    æĹĹä¸ĭ
    0.23
    æĹĹä¸ĭçļĦ
    0.23
    .com
    0.23
    çļĦ大
    0.21
    ®,
    0.21
     Morrow
    0.21
    Activations Density 0.495%

    No Known Activations