© 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. 1116
    Prev
    Next
    INDEX
    Explanations

    fashion trends

    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
    çļĦæķħäºĭ
    -0.09
    æķħäºĭ
    -0.09
    ä»ĺ
    -0.08
    ä¼łå¥ĩ
    -0.08
    éŨåīį
    -0.08
    ç»Ħè£ħ
    -0.08
    ä½ĵä¼ļ
    -0.08
    beh
    -0.08
    é£İ鼨
    -0.08
     Revel
    -0.08
    POSITIVE LOGITS
    è¶ĭåĬ¿
    0.18
    çļĦè¶ĭåĬ¿
    0.17
     trends
    0.14
    è¶ĭåIJij
    0.14
     trend
    0.14
    æµģè¡Į
    0.11
    æµģè¡ĮçļĦ
    0.11
    æ½®æµģ
    0.11
    缼è¡Į
    0.11
     Trends
    0.11
    Activations Density 0.058%

    No Known Activations