© 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. 13118
    Prev
    Next
    INDEX
    Explanations

    old-fashioned

    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
    éĿŀ常çļĦ
    -0.23
    ä»ĸå·²ç»ı
    -0.21
    æĪijä¸įçŁ¥éģĵ
    -0.21
    ä»ĸèĩªå·±
    -0.20
    广åijĬæľįåĬ¡
    -0.20
     fucking
    -0.20
    éĿŀ常好çļĦ
    -0.20
    éĿŀ常好
    -0.19
    apons
    -0.19
    æĪijèĩªå·±
    -0.19
    POSITIVE LOGITS
     your
    0.31
    ä½łçļĦ
    0.26
    your
    0.26
    æĤ¨çļĦ
    0.26
     ваÑĪего
    0.24
    å¿ĥ仪
    0.23
    รม
    0.22
     newfound
    0.21
     youre
    0.20
    io
    0.20
    Activations Density 0.162%

    No Known Activations