© 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. 1609
    Prev
    Next
    INDEX
    Explanations

    However, but

    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
     Bald
    -0.09
    说ä¸įå®ļ
    -0.09
     Ðijо
    -0.08
    å¿Ŀ
    -0.08
    caffold
    -0.08
    åĴ©
    -0.08
    èĢĮåIJİ
    -0.08
    è¿Ļåĩłä¸ª
    -0.08
    æīĢ以æĪij
    -0.08
    è£ĺ
    -0.08
    POSITIVE LOGITS
    ä¸įä»ħä»ħ
    0.10
    æĽ´éĩįè¦ģ
    0.10
    éģĹæĨ¾
    0.10
    æľĢéĩįè¦ģçļĦ
    0.09
    åIJĮæĹ¶ä¹Ł
    0.09
    究竣æĺ¯
    0.09
    究竣
    0.09
    Separated
    0.08
    quez
    0.08
    æĽ´éĩįè¦ģçļĦ
    0.08
    Activations Density 0.145%

    No Known Activations