© 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. 19275
    Prev
    Next
    INDEX
    Explanations

    opportunity to

    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
    æĦıæĢĿæĺ¯
    -0.10
    è·Ĺ
    -0.09
     Madden
    -0.09
    yers
    -0.09
    æļĿ
    -0.09
    çļĦ缮çļĦ
    -0.09
    主æŨ
    -0.09
    çļĦä¿¡ä»»
    -0.09
    æľīäºĨ
    -0.09
    没æľīåĬŀæ³ķ
    -0.09
    POSITIVE LOGITS
    terminal
    0.09
     immediate
    0.09
    éĹ®éĹ®
    0.09
    åľ¨ä¸Ģ
    0.09
    åľ¨åŃ¦æł¡
    0.09
     Sap
    0.08
    ë¶ģ
    0.08
    åľ¨æĪijçļĦ
    0.08
    æŁĦ
    0.08
     terminal
    0.08
    Activations Density 0.055%

    No Known Activations