© 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. 23346
    Prev
    Next
    INDEX
    Explanations

    same or similarly

    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
    äºĭåħĪ
    -0.10
     PURE
    -0.09
    kes
    -0.09
    chè
    -0.09
    æıIJåīį
    -0.09
    ç»ı纬
    -0.09
    Ñģов
    -0.09
     вне
    -0.09
    许å¤ļ人
    -0.09
    综
    -0.09
    POSITIVE LOGITS
    åIJĮæł·çļĦ
    0.33
    åIJĮæł·
    0.27
    åIJĮ樣
    0.23
     similarly
    0.22
    类似çļĦ
    0.22
    ä¹ŁåIJĮæł·
    0.21
     similar
    0.21
     same
    0.20
    ä¹Łæĺ¯å¦ĤæѤ
    0.20
    ä¸Ģæł·çļĦ
    0.19
    Activations Density 0.085%

    No Known Activations