© 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. 62787
    Prev
    Next
    INDEX
    Explanations

    we at

    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
    دÙĨÙĬ
    -0.09
    æ¯ı个人çļĦ
    -0.09
    åIJĦçķĮ
    -0.09
    æĤį
    -0.09
    è§ĴéĢIJ
    -0.08
    å¤©åľ°
    -0.08
    çļĤ
    -0.08
    å°±è¿Ļæł·
    -0.08
    ä¸ĩåIJį
    -0.08
    æĸĩåĮĸ建设
    -0.08
    POSITIVE LOGITS
    gos
    0.10
    bart
    0.09
    eil
    0.08
    åķ¼
    0.08
    棺
    0.08
    ç³ľ
    0.08
    [url
    0.08
    Ùħات
    0.08
    Elem
    0.08
    讯
    0.08
    Activations Density 0.011%

    No Known Activations