© 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. 13985
    Prev
    Next
    INDEX
    Explanations

    handball and basketball

    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
    structures
    -0.20
    strain
    -0.18
    _drv
    -0.18
     Majority
    -0.18
    æ¼Ĥ
    -0.18
    formance
    -0.18
    hem
    -0.18
    è¯Ńæĸĩ
    -0.17
    RM
    -0.17
    èĻŀ
    -0.17
    POSITIVE LOGITS
    çĨ¹
    0.19
    æijĦåĥı
    0.19
    ingt
    0.18
     пÑĢиÑĩ
    0.18
    éĥ¨éĥ¨éķ¿
    0.18
    erten
    0.18
    /XML
    0.18
    人寿
    0.18
    åįģäºĮæĿ¡
    0.18
    epad
    0.18
    Activations Density 0.001%

    No Known Activations