© 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. 52072
    Prev
    Next
    INDEX
    Explanations

    referring to

    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
    麻
    -0.11
    roc
    -0.10
    åĭĴ
    -0.09
    asar
    -0.09
    ertype
    -0.09
    çĶļèĩ³æĺ¯
    -0.09
    åłª
    -0.09
    æ´¾
    -0.09
    çĦ¶
    -0.09
    认æ¸ħ
    -0.09
    POSITIVE LOGITS
    æĮĩçļĦæĺ¯
    0.14
    æĺ¯æĮĩ
    0.12
    ä»Ģä¹ĪæĦıæĢĿ
    0.11
    æĮĩ
    0.11
     refers
    0.10
    sic
    0.10
    åĽłä¸ºåľ¨
    0.09
    æĮĩçĿĢ
    0.09
     ведÑĮ
    0.09
    çļĦæĦıæĢĿ
    0.09
    Activations Density 0.069%

    No Known Activations