© 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. 33927
    Prev
    Next
    INDEX
    Explanations

    thing happened, something new, turned out

    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
    踵
    -0.11
    çļĦä¸ĢäºĽ
    -0.09
    åĸľ
    -0.09
    èĬľ
    -0.09
    åı¦è¡Į
    -0.09
    ä¸Ģ个èģĮä¸ļ
    -0.08
     Quentin
    -0.08
     Rao
    -0.08
    .Extension
    -0.08
     strstr
    -0.08
    POSITIVE LOGITS
    ÑĦин
    0.09
    åľ¨äºİ
    0.09
    泡泡
    0.09
    æĪĸå¤ļ
    0.09
    ogne
    0.09
    elder
    0.09
    沧æ¡ij
    0.09
    à®´
    0.08
    奶ç²ī
    0.08
    rous
    0.08
    Activations Density 0.018%

    No Known Activations