© 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. 7737
    Prev
    Next
    INDEX
    Explanations

    permission of

    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
     kiá»ĩn
    -0.09
    ä¼ı
    -0.09
    acted
    -0.09
    èĭ¦
    -0.08
    裸
    -0.07
    quet
    -0.07
     обÑĭ
    -0.07
     correct
    -0.07
    moves
    -0.07
    ä¹Ļçĥ¯
    -0.07
    POSITIVE LOGITS
    izen
    0.10
    è¦ģæĬĬ
    0.09
    çľ¼åīį
    0.09
    лик
    0.09
    é¦ĸåħĪè¦ģ
    0.09
    æīª
    0.09
    èݼ
    0.09
    иÑĢование
    0.09
    åŃº
    0.09
    è¿ĽäºĨ
    0.09
    Activations Density 0.015%

    No Known Activations