© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7037
    Prev
    Next
    INDEX
    Explanations

    email headers or document beginnings

    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
    ÙĦج
    -0.09
    å¾ĢåIJİ
    -0.09
    åIJ¼
    -0.09
    ä½ĽéĻĢ
    -0.09
    oyal
    -0.09
    onis
    -0.09
    举
    -0.09
    occasion
    -0.09
    iaÅĤ
    -0.09
    åĪİ
    -0.08
    POSITIVE LOGITS
     ÑģобÑģÑĤвенно
    0.09
    æĹĮ
    0.08
    笳
    0.08
    åįĪé¤IJ
    0.08
    èĬ±æł·
    0.07
    ones
    0.07
    icl
    0.07
    åħ¼é¡¾
    0.07
    好çļĦ
    0.07
    .yy
    0.07
    Activations Density 0.216%

    No Known Activations