© 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. 52478
    Prev
    Next
    INDEX
    Explanations

    instead of

    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
    ä¹IJæĦı
    -0.09
    ä¼ļå±ķ
    -0.09
    幺
    -0.09
    ä¸įè¦ģ太
    -0.09
    åĬ©
    -0.09
     Meyer
    -0.09
    æĺ¯ä¸įä¼ļ
    -0.09
    饷
    -0.08
    èĩªæĿ¥æ°´
    -0.08
    æĸ¹åı¯
    -0.08
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.19
    åıįèĢĮ
    0.10
    åįķ纯çļĦ
    0.10
    ç´ł
    0.10
     sondern
    0.09
     вмеÑģÑĤ
    0.09
    åºĶæľīçļĦ
    0.09
     rall
    0.09
    åıįåĢĴ
    0.09
    çĨŁæĤīçļĦ
    0.09
    Activations Density 0.036%

    No Known Activations