© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51233
    Prev
    Next
    INDEX
    Explanations

    as a

    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
    åIJĮä»ģ
    -0.11
     downright
    -0.09
    æĭĨ
    -0.09
    窮
    -0.09
    лиÑĤ
    -0.09
    è¿Ļåĩłä¸ª
    -0.08
    æĥķ
    -0.08
    çļĨ
    -0.08
    èĢĮéĿŀ
    -0.08
    åĢı
    -0.08
    POSITIVE LOGITS
    ä½ľä¸º
    0.13
    à¹ĥà¸Ļà¸IJาà¸Ļะ
    0.13
    身为
    0.12
    ä½ľä¸ºä¸Ģ个
    0.12
    ä½ľä¸ºä¸ĢåIJį
    0.11
    ä½ľçĤº
    0.11
    åħ¸åŀĭçļĦ
    0.10
    ä½ľä¸ºä¸Ģç§į
    0.10
    å·´å·´
    0.09
     единÑģÑĤв
    0.09
    Activations Density 0.062%

    No Known Activations