© 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. 20739
    Prev
    Next
    INDEX
    Explanations

    states of knowing or stating facts

    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¸Ģæĸ¹éĿ¢
    -0.10
     конеÑĩно
    -0.09
    4
    -0.09
    羣çļĦæĺ¯
    -0.09
    9
    -0.09
    3
    -0.08
    6
    -0.08
    åı¯è°ĵæĺ¯
    -0.08
    2
    -0.08
    8
    -0.08
    POSITIVE LOGITS
    缸åºĶçļĦ
    0.09
    ä¹ŁåºĶ该
    0.09
    çļĦ形象
    0.09
    çݯåį«
    0.09
    è¶ĬæĿ¥è¶Ĭå°ij
    0.09
    缸符
    0.09
     ISO
    0.09
    upa
    0.08
     equally
    0.08
    ÐŁÐ¾Ð´ÑĢоб
    0.08
    Activations Density 0.136%

    No Known Activations