© 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. 49773
    Prev
    Next
    INDEX
    Explanations

    construction, design, mode, position, payment, rig, play

    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
    æīĢåľ¨çļĦ
    -0.09
    æĹ¥å¸¸å·¥ä½ľ
    -0.09
    PPER
    -0.08
    ç´ĭ
    -0.08
    çļĦåľ°æŃ¥
    -0.08
    _GU
    -0.08
    ãĤ¢ãĥĬ
    -0.08
    arkers
    -0.08
    佬
    -0.08
    æł¹æį®ä¸įåIJĮ
    -0.08
    POSITIVE LOGITS
    æĸ¹å¼ı
    0.17
    庶
    0.10
    æĸ¹æ³ķ
    0.10
    屯
    0.09
     biç
    0.09
     ë°©ë²ķ
    0.09
    漫
    0.09
    å½¢å¼ı
    0.09
    æīĭæ³ķ
    0.09
    ë²ķ
    0.09
    Activations Density 0.483%

    No Known Activations