© 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. 14546
    Prev
    Next
    INDEX
    Explanations

    good, serious, modern, right, great followed by noun

    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
    åIJĦç§įåIJĦæł·
    -0.20
    Various
    -0.20
    æľªçŁ¥
    -0.19
    åIJĦç§į
    -0.19
    åİŁ
    -0.19
    æĽ´å®¹æĺĵ
    -0.19
    oma
    -0.18
    ERIC
    -0.18
    é£ı
    -0.18
    lu
    -0.18
    POSITIVE LOGITS
    æĩĤå¾Ĺ
    0.23
    æĻĵå¾Ĺ
    0.22
    åIJĪæł¼
    0.21
    gó
    0.21
     sane
    0.21
    家éĥ½çŁ¥éģĵ
    0.20
    è¶ĬæĿ¥è¶Ĭå°ij
    0.20
    æĢ»æĺ¯
    0.19
     understanding
    0.19
    æŃ£å¸¸çļĦ
    0.19
    Activations Density 0.074%

    No Known Activations