© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31082
    Prev
    Next
    INDEX
    Explanations

    software and services

    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
    afs
    -0.10
    ç»Ļåĩº
    -0.10
    é«ĺ楼
    -0.10
    èļĮ
    -0.09
    æĹłå£°
    -0.09
    寸
    -0.09
    åijĬè¯īä½ł
    -0.09
    æµģéĢļ
    -0.09
    建设çĶ¨åľ°
    -0.09
    /to
    -0.08
    POSITIVE LOGITS
    æĬĢæľ¯æĶ¯æĮģ
    0.11
     kepada
    0.11
     insight
    0.10
    åħħ足çļĦ
    0.10
     opportunities
    0.10
     ÑĥÑģлÑĥги
    0.10
    çļĦæľºä¼ļ
    0.10
    æľºä¼ļ
    0.09
    缴èĩ³
    0.09
    å®īåħ¨ä¿Ŀéļľ
    0.09
    Activations Density 0.355%

    No Known Activations