© 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. 6572
    Prev
    Next
    INDEX
    Explanations

    note buyers

    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
    å¤ļä¸ªåĽ½å®¶
    -0.10
    åĮĹ京å¸Ĥ
    -0.10
    å¹´éĻIJ
    -0.10
     Sach
    -0.09
    éªij
    -0.09
    鹬
    -0.08
    æĿijåħļæĶ¯éĥ¨
    -0.08
    æ»ĺ
    -0.08
    æĤ¨åIJĮæĦı
    -0.08
     Pam
    -0.08
    POSITIVE LOGITS
    -area
    0.12
    å¸Ĥ
    0.12
    èģĮä¸ļæĬĢæľ¯
    0.12
    å¸Ĥãģ®
    0.10
    ç±į
    0.10
    æĹ¥æĬ¥
    0.10
    ìĭľ
    0.10
    ä¹ĥèĩ³
    0.10
    æĹ¥æĬ¥ç¤¾
    0.09
    ocity
    0.09
    Activations Density 0.115%

    No Known Activations