© 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. 37095
    Prev
    Next
    INDEX
    Explanations

    Union County, Medical, Compilation

    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
    黾
    -0.09
    è¦ģä¹Ī
    -0.09
    é¹°
    -0.09
    éĻ
    -0.09
    ç«Ł
    -0.08
    åħ¨éķĩ
    -0.08
    åħ¨çľģ
    -0.08
    ä¸įå½ĵ
    -0.08
    æ¶ĪéĻ¤
    -0.08
    第äºĮ大
    -0.08
    POSITIVE LOGITS
    finger
    0.10
    TestClass
    0.09
    æĶ¿åºľéĥ¨éŨ
    0.09
    quet
    0.09
    é»Ħ
    0.09
    vere
    0.08
    ноÑģÑĤ
    0.08
    éģ£
    0.08
    пал
    0.08
    ombo
    0.08
    Activations Density 0.015%

    No Known Activations