© 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. 4259
    Prev
    Next
    INDEX
    Explanations

    he [verb]

    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
     Phụ
    -0.10
    ä¸įä¸Ģæł·çļĦ
    -0.10
    åIJįèªī
    -0.09
    榷
    -0.09
    egis
    -0.09
    æĸ¹éĿ¢çļĦ
    -0.09
    ä¸įä¸Ģæł·
    -0.09
    宿
    -0.09
    åIJī
    -0.09
    è¸Ķ
    -0.09
    POSITIVE LOGITS
    ä¿ĿæĮģçĿĢ
    0.09
    åħ·å¤ĩ
    0.09
    ä½įåĪĹ
    0.09
    olle
    0.09
    ault
    0.08
    Ùħرا
    0.08
    累计
    0.08
    åĽĬ
    0.08
     Susp
    0.08
     Grü
    0.08
    Activations Density 0.042%

    No Known Activations