© 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. 51713
    Prev
    Next
    INDEX
    Explanations

    organizations and place names

    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
    åĴĮæĬĢæľ¯
    -0.09
    éĥ¨å§Ķ
    -0.09
    æĭ§
    -0.09
    éķ¬
    -0.09
    horse
    -0.09
    é©´
    -0.09
    ç§ijæĬĢèĤ¡ä»½
    -0.08
    лÑĮ
    -0.08
    èıģ
    -0.08
    oted
    -0.08
    POSITIVE LOGITS
    çĽ´è¾¾
    0.09
    åīį端
    0.09
    溢
    0.09
    æģIJ
    0.08
    âĪķ
    0.08
    åĽ½éĻħæľºåľº
    0.08
    ä½ĵ系建设
    0.08
    åĽŀ头
    0.08
    寺
    0.08
    parator
    0.08
    Activations Density 0.055%

    No Known Activations