© 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. 13297
    Prev
    Next
    INDEX
    Explanations

    inferior opponent, Lanka, trailing by, stuck in

    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
    vor
    -0.20
    çıº
    -0.18
    ä¼ijåģĩ
    -0.18
    SS
    -0.18
    çݯ
    -0.18
    oss
    -0.18
    åľ°éĿ¢
    -0.17
    æľīåIJįçļĦ
    -0.17
    ä¸ĭè¾¾
    -0.17
    ercul
    -0.17
    POSITIVE LOGITS
    央
    0.21
    被æ·ĺæ±°
    0.19
    коÑģ
    0.19
    æ·ĺæ±°
    0.19
    æĭIJ
    0.19
    åºĨ幸
    0.19
    PLUS
    0.18
    åıªèĥ½
    0.18
    æ¯Ļ
    0.18
    Logo
    0.18
    Activations Density 0.147%

    No Known Activations