© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51506
    Prev
    Next
    INDEX
    Explanations

    names like de Meneses, de Abreu, de León

    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
    ä»İä¸Ń
    -0.09
    说çļĦæĺ¯
    -0.09
    uden
    -0.09
    ieve
    -0.09
    èĭįçϽ
    -0.09
    è¡Ĺéģĵ
    -0.08
    对åħ¶è¿Ľè¡Į
    -0.08
    ç͍æĿ¥
    -0.08
    irie
    -0.08
    éĻŁ
    -0.08
    POSITIVE LOGITS
    åħ¶æ¬¡
    0.09
    çĶ¨å¾®ä¿¡
    0.08
    è¿Ļç¯ĩæĸĩ竳
    0.08
    oses
    0.08
    inia
    0.08
    æĮŁ
    0.08
    cratch
    0.07
    ithe
    0.07
    èį£å¹¸
    0.07
    ÏĬ
    0.07
    Activations Density 0.070%

    No Known Activations