© 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. 49489
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    lus
    -0.09
    éĩį
    -0.09
    ä»Ģä¹Īéĥ½ä¸į
    -0.09
    éªĦ
    -0.08
    è¿Ļ两年
    -0.08
    æĭīæĸ¯
    -0.08
    åĽ½åĬ¡
    -0.08
    åįİ举
    -0.08
    çļĦçĥŃæĥħ
    -0.08
     Peterson
    -0.08
    POSITIVE LOGITS
    ç¡
    0.09
    åĹĵåŃIJ
    0.09
    ousse
    0.09
    _BINDING
    0.09
    衬
    0.09
    缼åħ¸
    0.09
    pill
    0.09
    anske
    0.08
    wat
    0.08
    achie
    0.08
    Activations Density 0.016%

    No Known Activations