© 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. 15937
    Prev
    Next
    INDEX
    Explanations

    biological and medical processes

    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
    èĥ½åĬĽåĴĮ
    -0.23
    æĻ¨æĬ¥
    -0.21
    ç»ıéªĮåĴĮ
    -0.21
    olph
    -0.20
    èĢĮè¿Ļ
    -0.20
    并ä¸Ķ
    -0.20
    åij¼åĴĮ
    -0.20
    ä¼ģä¸ļåĴĮ
    -0.19
    èĢĮä¸Ķ
    -0.19
     STATS
    -0.19
    POSITIVE LOGITS
    çļĦåħ³ç³»
    0.24
    orny
    0.20
    çļĦçIJĨ解
    0.20
    visibility
    0.19
    缩
    0.19
    urv
    0.19
    è´£
    0.18
    å¾Ĥ
    0.18
    侥幸
    0.18
    ä¸įæŃ»
    0.18
    Activations Density 0.195%

    No Known Activations