© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12011
    Prev
    Next
    INDEX
    Explanations

    NO, failed, continue, Remember

    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
    ä¹Łä¸įéĶĻ
    -0.10
    éĻªä½ł
    -0.10
    éĻª
    -0.10
    æĿª
    -0.09
    ä¸įèĩ³äºİ
    -0.09
    è¿ĺæĮº
    -0.09
    è¿ĺä¸įéĶĻ
    -0.09
    ãĤĤãģĤãĤĬ
    -0.09
    工夫
    -0.09
    å§Ĭ妹
    -0.08
    POSITIVE LOGITS
    ä¸į顾
    0.10
    åĽ¢ä¼Ļ
    0.10
    导èĩ´
    0.09
    åħ¸åŀĭçļĦ
    0.09
    è·µ
    0.09
    apel
    0.09
    令人
    0.09
    kah
    0.09
    åħ¸åŀĭ
    0.09
    ä¼ģåĽ¾
    0.08
    Activations Density 0.074%

    No Known Activations