© 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. 20726
    Prev
    Next
    INDEX
    Explanations

    managing / management

    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
    大èĥĨ
    -0.10
    认åı¯
    -0.09
    è´¡çĮ®
    -0.08
    åħ±åIJĮåĬªåĬĽ
    -0.08
    é¢ĺ主
    -0.08
    è¯
    -0.08
    ฯ
    -0.08
    ares
    -0.08
    æĬĢæľ¯æĶ¯æĮģ
    -0.08
    庶
    -0.08
    POSITIVE LOGITS
    è¿ĩ渡
    0.12
    åį±æľº
    0.10
    æ¸IJ
    0.10
    è¿Ļ段
    0.09
    èĪª
    0.09
    éĴľ
    0.09
    æĦī
    0.09
    orch
    0.09
    æ´ĭ
    0.09
    æ±¹
    0.09
    Activations Density 0.057%

    No Known Activations