© 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. 58145
    Prev
    Next
    INDEX
    Explanations

    leading or leader

    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
    bole
    -0.10
    yun
    -0.09
    ersed
    -0.08
    辩
    -0.08
     Thumbnails
    -0.08
    解éĻ¤
    -0.08
    æĭĵ
    -0.08
    illegal
    -0.08
    [strlen
    -0.08
    ive
    -0.08
    POSITIVE LOGITS
    å¼ķé¢Ĩ
    0.11
    Leading
    0.11
    é¢Ĩè¡Ķ
    0.11
    çļĦ带é¢Ĩä¸ĭ
    0.10
    带头
    0.10
    é¢Ĩè·ij
    0.10
    å·¾
    0.09
    éłĺ
    0.09
     leading
    0.09
     Leading
    0.09
    Activations Density 0.120%

    No Known Activations