© 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. 34021
    Prev
    Next
    INDEX
    Explanations

    plot details

    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
    æĹºçĽĽ
    -0.10
    å¸Ĥåľºç«ŀäºī
    -0.10
    åħħ足çļĦ
    -0.09
    ä¸ĢæĿ¡é¾Ļ
    -0.09
    ä¸īæĿ¡
    -0.09
    ancement
    -0.09
    ä¸ĢæµģçļĦ
    -0.08
    à¹ĥà¸ļ
    -0.08
    plies
    -0.08
    enne
    -0.08
    POSITIVE LOGITS
    åħ±éĿĴåĽ¢
    0.09
    äºĭ项
    0.09
    æĿĸ
    0.09
    åIJĪéĩij
    0.08
    å¤ļå¤ļ
    0.08
     squad
    0.08
    æĹłä¸į
    0.08
    裴
    0.08
    辩è¯ģ
    0.08
    åĨľåľº
    0.08
    Activations Density 0.004%

    No Known Activations