© 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. 14465
    Prev
    Next
    INDEX
    Explanations

    metal element roman numerals

    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
     dialect
    -0.20
    æīĵ好
    -0.20
    ä¸ĭæīĭ
    -0.20
    è¿Ļåı¥è¯Ŀ
    -0.19
    åĭĩæķ¢
    -0.19
    è°ĥæķ´
    -0.18
    ä¸įå¼Ģ
    -0.18
    è¾¹éĻħ
    -0.18
    RESS
    -0.18
    æĪIJ交
    -0.18
    POSITIVE LOGITS
    åIJĬ顶
    0.20
    веÑĩ
    0.20
    æ±Ľ
    0.19
    _capture
    0.18
    æĭĦ
    0.18
     Blanco
    0.18
     Chall
    0.18
    ç°¸
    0.18
    _except
    0.18
    çĹĶ
    0.18
    Activations Density 0.153%

    No Known Activations