© 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. 10425
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åIJĦè¡ĮåIJĦä¸ļ
    -0.10
    è¾ĺ
    -0.10
    æĻļæĬ¥
    -0.10
    iran
    -0.09
    æīĢåľ¨
    -0.09
    acle
    -0.09
    åIJ
    -0.09
    åIJĦå¼Ĥ
    -0.09
    less
    -0.09
    è¦ģåѦä¼ļ
    -0.09
    POSITIVE LOGITS
    sons
    0.10
    zig
    0.08
     quot
    0.08
     Moderator
    0.08
    å°±éľĢè¦ģ
    0.08
    iew
    0.08
    ·»
    0.08
    пиÑĤ
    0.08
    eron
    0.08
    ije
    0.08
    Activations Density 0.004%

    No Known Activations