© 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. 51564
    Prev
    Next
    INDEX
    Explanations

    first time

    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
    çĹĺ
    -0.09
    æĺ¯æľĢ好çļĦ
    -0.08
    åĢĺ
    -0.08
    èħº
    -0.08
    éļ¨æĻĤ
    -0.08
    éļıæŶ
    -0.08
    деÑĢжива
    -0.08
    åIJ¦
    -0.08
    æĽ´å¥½çļĦ
    -0.08
    stab
    -0.08
    POSITIVE LOGITS
    èĦ¾æ°Ķ
    0.10
    è¿Ļä¹Ī大
    0.10
    ä¸ŃåŃĺåľ¨çļĦ
    0.10
    æĺ¯åľ¨
    0.09
    æĦıä¹īä¸ĬçļĦ
    0.09
    _ALLOWED
    0.09
    è¿Ļä¹Īå¤ļ
    0.09
    icable
    0.09
    èĮħ
    0.09
    èĭ±æĸĩ
    0.08
    Activations Density 0.082%

    No Known Activations