© 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. 58226
    Prev
    Next
    INDEX
    Explanations

    names following 'and' or '&'

    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
    opp
    -0.09
    åĽĽé¡¹
    -0.09
    æĦģ
    -0.09
    两项
    -0.08
    太太
    -0.08
    媳å¦ĩ
    -0.08
    çIJĨ解åĴĮ
    -0.08
    æľį
    -0.08
    çļĦ妻åŃIJ
    -0.08
     Holdings
    -0.08
    POSITIVE LOGITS
    åĥļ
    0.09
    ä»ĸ人
    0.09
     ÑĥÑģили
    0.09
    æĺĻ
    0.09
    paged
    0.09
    ãģ£ãģĵ
    0.08
    è·Łä½ł
    0.08
    lider
    0.08
    ä¼ļåIJĮ
    0.08
    ä¹ĭäºī
    0.08
    Activations Density 0.141%

    No Known Activations