© 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. 50026
    Prev
    Next
    INDEX
    Explanations

    listing examples

    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
    anst
    -0.09
    è¿ĺä¸įæĺ¯
    -0.09
    atter
    -0.09
    èİĵ
    -0.09
    éļıä¹ĭ
    -0.09
    å¼ĢåIJ¯äºĨ
    -0.09
    è¾ŀ
    -0.09
    éħĹ
    -0.09
    åĶ§
    -0.09
    ç¼Ł
    -0.08
    POSITIVE LOGITS
    ä¸ĢäºĽ
    0.10
    åĩ«
    0.09
    æĹ¢æľī
    0.09
    æĿ¥èĩª
    0.08
    æ¸ł
    0.08
    äºĶ大
    0.08
    ä¸įä¹ı
    0.08
     some
    0.08
    åı¯éĿł
    0.08
    èĢĮä¸Ķ
    0.08
    Activations Density 0.081%

    No Known Activations