© 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. 5716
    Prev
    Next
    INDEX
    Explanations

    look, new, furnished

    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
    æīĢéľĢè¦ģçļĦ
    -0.11
    æīĢéľĢè¦ģ
    -0.10
    æĥħåĨµæĿ¥çľĭ
    -0.10
    éĤ£æł·
    -0.10
    æīĢæıIJä¾ĽçļĦ
    -0.10
    åħ¶ä»ĸçļĦ
    -0.09
    é¢ĩæľī
    -0.09
    çļĦæĸ¹å¼ıæĿ¥
    -0.09
    å®ŀåľ¨æĺ¯å¤ª
    -0.09
    没æľīä»Ģä¹Ī
    -0.09
    POSITIVE LOGITS
    æĢ§å¼º
    0.13
    èĥ½åĬĽå¼º
    0.12
    è¿ĩåIJİ
    0.10
    æľīæľŁ
    0.10
    æĿ¡ä»¶ä¸ĭ
    0.09
    åĮ£
    0.09
     знаÑĩиÑĤ
    0.09
    onde
    0.09
    arring
    0.08
    æķ°æį®æĺ¾ç¤º
    0.08
    Activations Density 0.395%

    No Known Activations