© 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. 20906
    Prev
    Next
    INDEX
    Explanations

    Short abbreviations

    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
    缯
    -0.11
    ç»
    -0.09
    aku
    -0.09
    ç¼ģ
    -0.09
    è¦ĥ
    -0.08
    ÑĮ
    -0.08
    æ²īæ·Ģ
    -0.08
    lund
    -0.08
    ç»ıéĶĢ
    -0.08
    estro
    -0.08
    POSITIVE LOGITS
    æĪ´
    0.10
    åħ¶éĹ´
    0.10
    ä¸Ģçķª
    0.09
    ÑĤол
    0.09
    ä¸įéĢĤåIJĪ
    0.09
    æĪIJå°±æĦŁ
    0.09
    ableView
    0.09
    æĺ¯ä¸įåı¯èĥ½
    0.09
    æĴĩ
    0.09
    ä¸įçĽ¸ä¿¡
    0.08
    Activations Density 0.214%

    No Known Activations