© 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. 55267
    Prev
    Next
    INDEX
    Explanations

    programming libraries and modules

    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
    举
    -0.09
    jdbc
    -0.09
     UObject
    -0.09
    æĮīè§Ħå®ļ
    -0.09
    endir
    -0.09
     EIF
    -0.09
    ä¹Ŀ大
    -0.08
    客åķĨ
    -0.08
     wholes
    -0.08
    Twig
    -0.08
    POSITIVE LOGITS
    åºĵ
    0.12
    /import
    0.11
    第ä¸īæĸ¹
    0.11
    åĮħ
    0.10
    sez
    0.10
     cầm
    0.09
    翼
    0.09
    庫
    0.09
     library
    0.09
    åºĵéĩĮ
    0.09
    Activations Density 0.884%

    No Known Activations