© 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. 37587
    Prev
    Next
    INDEX
    Explanations

    Ecuador and Colombia

    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
    less
    -0.10
    lessly
    -0.10
    iture
    -0.10
    å»ĵ
    -0.09
    çħ
    -0.09
    á»ģm
    -0.09
     ÑĥÑģп
    -0.08
    icates
    -0.08
    åIJ®
    -0.08
    秦çļĩ
    -0.08
    POSITIVE LOGITS
    çħ¦
    0.10
    ä¸įæĿ¥
    0.09
    -born
    0.09
    è¿Ļä¸ªåľ°æĸ¹
    0.09
    stor
    0.09
    æ¯ıéļĶ
    0.09
    å¢ĥ
    0.09
    ität
    0.09
     McL
    0.08
     Lamar
    0.08
    Activations Density 0.009%

    No Known Activations