© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52211
    Prev
    Next
    INDEX
    Explanations

    manage, create, plan, select, organize

    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
    ãng
    -0.10
    åįĩ
    -0.08
    糯
    -0.08
    åŃIJåŃĻ
    -0.08
    åģļä¸ĢäºĽ
    -0.08
    æĪIJ为ä¸ĢåIJį
    -0.08
    IFS
    -0.08
    .fast
    -0.07
    ilon
    -0.07
     Symphony
    -0.07
    POSITIVE LOGITS
    并éĢļè¿ĩ
    0.10
    并
    0.10
    åĴĮåıijå±ķ
    0.10
    èĭĵ
    0.10
    并ä¸İ
    0.10
    ､
    0.09
     and
    0.09
    并对
    0.09
    并åIJij
    0.09
    建设åĴĮ
    0.09
    Activations Density 0.371%

    No Known Activations