© 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. 21977
    Prev
    Next
    INDEX
    Explanations

    understanding and services

    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
    èĤī
    -0.08
    妾
    -0.08
    à¹Ģà¸Ĺศ
    -0.08
    åĦ¿
    -0.08
    æĬ¼
    -0.08
     Alle
    -0.08
    WE
    -0.08
    .gca
    -0.07
    SCO
    -0.07
     Muk
    -0.07
    POSITIVE LOGITS
    çĶŁæ´»è´¨éĩı
    0.10
    åİĨåı²æĸĩåĮĸ
    0.10
    çĶŁäº§ç»ıèIJ¥
    0.10
    çĶŁäº§çĶŁæ´»
    0.09
    æķijæĬ¤
    0.09
    å®£ä¼łæ´»åĬ¨
    0.09
    缸åħ³è´Łè´£
    0.09
    ç¼Ń
    0.09
    ç»ıæµİæĬĢæľ¯
    0.09
    åIJĦé¡¹å·¥ä½ľ
    0.09
    Activations Density 0.593%

    No Known Activations