© 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. 18813
    Prev
    Next
    INDEX
    Explanations

    life contexts

    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
    åĶ¿
    -0.10
    äºĭåIJİ
    -0.09
    orse
    -0.09
    ç§ģèĩª
    -0.09
    æľĢ好æĺ¯
    -0.09
    笥
    -0.08
    秾
    -0.08
    tur
    -0.08
    çļĦ人æĿ¥è¯´
    -0.08
    大åĬĽæİ¨è¿Ľ
    -0.08
    POSITIVE LOGITS
    é»ijå¤ľ
    0.10
    è¿ĶåĽŀæIJľçĭIJ
    0.09
    ãĢĤ↵
    0.09
    åĵ¦
    0.08
    ãĢĤ↵↵
    0.08
    æ£ķèī²
    0.08
     лÑİб
    0.08
    ModuleName
    0.08
    æĹ¢æĺ¯
    0.08
    .↵
    0.08
    Activations Density 0.348%

    No Known Activations