© 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. 20604
    Prev
    Next
    INDEX
    Explanations

    logic and reason

    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
    å®ļä½į
    -0.09
    èĢĺ
    -0.09
     Trom
    -0.09
    лон
    -0.08
    illion
    -0.08
    ä¸į说
    -0.08
    æ±Ģ
    -0.08
     Fishing
    -0.08
    éĴĵ
    -0.08
    arus
    -0.08
    POSITIVE LOGITS
    ä¸¥æł¼çļĦ
    0.11
    eration
    0.10
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.10
    éĢ»è¾ij
    0.09
    æݨçIJĨ
    0.09
    æħĬ
    0.09
     hexadecimal
    0.09
     ÑģÑĤал
    0.09
    è¨İ
    0.09
    å·¥åķĨå±Ģ
    0.08
    Activations Density 0.018%

    No Known Activations