© 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. 49620
    Prev
    Next
    INDEX
    Explanations

    after

    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
    .dex
    -0.09
    è¿Ļ个æŶåĢĻ
    -0.09
    æĺ¯ä¸ª
    -0.09
    æĴ¥
    -0.09
    æĺ¯æľī
    -0.09
    åŃĺåľ¨
    -0.09
    ä¸įåı¯ä»¥
    -0.09
    ELY
    -0.08
    ÑĮ
    -0.08
    æĺ¯ä¸Ģéĥ¨
    -0.08
    POSITIVE LOGITS
    ä¹ĭä½Ļ
    0.10
    çļĦåIJĮæŶ
    0.10
    æĪijåıĪ
    0.09
     ÑģеÑĤ
    0.08
    ä½İä½į
    0.08
    æĪijæĬĬ
    0.08
     kami
    0.08
    产
    0.08
    èĬ
    0.08
    æĬĬå®ĥ
    0.08
    Activations Density 0.135%

    No Known Activations