© 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. 6778
    Prev
    Next
    INDEX
    Explanations

    at the time

    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
    /lg
    -0.10
    æĸ¹éĿ¢
    -0.10
    boom
    -0.09
    abo
    -0.09
    åĶī
    -0.08
    æĸ¹éĿ¢çļĦ
    -0.08
    èĩ³äºİ
    -0.08
    æĹ¶å¸¸
    -0.08
    è§Ĵ度æĿ¥çľĭ
    -0.08
    è¿Ļæł·çļĦè¯Ŀ
    -0.08
    POSITIVE LOGITS
     вÑģей
    0.09
    owi
    0.09
    roker
    0.09
    ringe
    0.08
    ä¹Ŀå¹´
    0.08
    kiem
    0.08
    æµģè¡ĮçļĦ
    0.08
     Manufact
    0.08
    ë¡ľìĦľ
    0.08
    缼
    0.08
    Activations Density 0.019%

    No Known Activations