© 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. 27059
    Prev
    Next
    INDEX
    Explanations

    you following punctuation

    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
    ç»ĻäºĪ
    -0.10
    ç»ĻäºĪäºĨ
    -0.09
    æµĴ
    -0.09
     Rud
    -0.09
    mgr
    -0.08
    æ¥ļ
    -0.08
    æĮĤçĿĢ
    -0.08
    é¦Ĺ
    -0.08
    ikut
    -0.08
    acia
    -0.08
    POSITIVE LOGITS
    æĹłè®ºæĺ¯
    0.10
    便æĺ¯
    0.09
    è¿Ļéĥ¨
    0.09
    åįıä¼ļä¼ļåijĺ
    0.09
    æĭ¥
    0.09
    ä¾Ĺ
    0.09
    clidean
    0.08
    èĢĻ
    0.08
    ìĸ¼
    0.08
    å¼ķæĿ¥
    0.08
    Activations Density 0.024%

    No Known Activations