© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37892
    Prev
    Next
    INDEX
    Explanations

    sales

    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
     nữa
    -0.10
    åīįéĢĶ
    -0.10
    æ¯ıéļĶ
    -0.10
    åķģ
    -0.10
    æľªæĿ¥
    -0.09
    æĿŀ
    -0.09
    éªIJ
    -0.09
    纵
    -0.09
    ä¸ĭä¸ĢæŃ¥
    -0.09
    楮
    -0.09
    POSITIVE LOGITS
    è´¡çĮ®
    0.09
    DAC
    0.08
    åı³è¾¹
    0.08
    ä¸ī个æĸ¹éĿ¢
    0.08
     outweigh
    0.08
     Bett
    0.08
    å¢ŀåĬłäºĨ
    0.07
     Ning
    0.07
    禾
    0.07
    æ¯Ķéĩį
    0.07
    Activations Density 0.202%

    No Known Activations