© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15275
    Prev
    Next
    INDEX
    Explanations

    officials said

    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
    ç»ıå¼Ģ
    -0.20
    大家åı¯ä»¥
    -0.20
    çļĦåIJĦç§į
    -0.19
    åIJĦç§į
    -0.19
    å½¢æĪIJçļĦ
    -0.18
    éĿŀ常çļĦ
    -0.18
    ä¸ĩäºĭ
    -0.18
    åħīèį£
    -0.18
    æµĵæµĵ
    -0.17
    miss
    -0.17
    POSITIVE LOGITS
    è¿Ļè¯Ŀ
    0.23
     notwithstanding
    0.22
    ä¹³
    0.20
    åĨį说
    0.19
    ä½ķåĨµ
    0.19
    èĢ³
    0.19
    ä¸Ĭãģ§
    0.18
    _OPERATION
    0.18
    æµ·è¾¹
    0.18
    ÈĻ
    0.17
    Activations Density 0.050%

    No Known Activations