© 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. 37262
    Prev
    Next
    INDEX
    Explanations

    its/their name

    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
    dess
    -0.09
    ields
    -0.09
    æݨä»ĭ
    -0.09
    äºĶå®ĺ
    -0.09
     оÑĢганизм
    -0.09
     необÑħодимо
    -0.09
    dom
    -0.09
    ensus
    -0.09
    cheid
    -0.08
    apon
    -0.08
    POSITIVE LOGITS
    æĿ¥èĩªäºİ
    0.10
    æĺ¯ä»İ
    0.09
    è¿Ļ个åIJįåŃĹ
    0.09
    åIJįåĪĹ
    0.09
    عÙĨ
    0.09
    à¸Īาà¸ģà¸ģาร
    0.09
     MEM
    0.08
    ç»IJ
    0.08
    ä¹ĭæīĢ以
    0.08
    ä¹Łè®¸æĺ¯
    0.08
    Activations Density 0.089%

    No Known Activations