© 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. 36601
    Prev
    Next
    INDEX
    Explanations

    based on classification criteria

    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
    ä¸į便
    -0.09
    éķ¦
    -0.09
     Berkshire
    -0.09
    è¿ľæĸ¹
    -0.08
     ÑģлÑĥÑĩа
    -0.08
    uve
    -0.08
     Wear
    -0.08
    主æµģ
    -0.08
     RESERVED
    -0.08
    颦
    -0.08
    POSITIVE LOGITS
    çļĦåĽłç´ł
    0.12
     criteria
    0.12
     criter
    0.12
    (criteria
    0.11
    æĺ¯åIJ¦æľī
    0.11
    criteria
    0.11
    åŁºäºİ
    0.11
     criterion
    0.11
    ä¾Ŀæį®
    0.11
     based
    0.10
    Activations Density 0.271%

    No Known Activations