© 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. 54168
    Prev
    Next
    INDEX
    Explanations

    proper names following "named"

    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
    rossover
    -0.09
    çľ¼çļ®
    -0.08
    çľ¼è§Ĵ
    -0.08
    çݰ身
    -0.08
    ä¸Ģéĺµ
    -0.08
    æķ´é¡¿
    -0.08
    éĺµèIJ¥
    -0.08
    æĸ°éĹ»ç½ij
    -0.08
    ä¸ĢæĶ¯
    -0.08
    pies
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.11
    IgnoreCase
    0.10
    ãģĭãģªãģĦ
    0.09
    ç®Ģ
    0.09
    togroup
    0.09
    té
    0.09
    /loader
    0.08
    çħ
    0.08
    æªĢ
    0.08
    getTable
    0.08
    Activations Density 0.028%

    No Known Activations