© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36784
    Prev
    Next
    INDEX
    Explanations

    identifying errors and criticisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ä¸ĢæŶ
    -0.11
    Tes
    -0.10
    æŶæĬ¥
    -0.09
    еÑģÑĤв
    -0.08
     اÙĦÙĥر
    -0.08
     окÑĢÑĥ
    -0.08
     Lah
    -0.08
    æī¿åĬŀ
    -0.08
    就好äºĨ
    -0.08
     пÑĢедназ
    -0.08
    POSITIVE LOGITS
    æ¶īå«Į
    0.13
    è´¨çĸij
    0.11
    æĪij认为
    0.11
    åľ¨æĪijçľĭæĿ¥
    0.11
    缺ä¹ı
    0.10
    ä¸įåIJĪ
    0.10
    æĪijè§īå¾Ĺ
    0.10
    缺å°ij
    0.09
    æĺİæĺ¾çļĦ
    0.09
    è¿ĺæľīå¾Īå¤ļ
    0.09
    Activations Density 0.157%

    No Known Activations