© 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. 11169
    Prev
    Next
    INDEX
    Explanations

    emotions and states of being

    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
    ä¸įä»ħ
    -0.11
    ä¸įåĥħ
    -0.10
    ä¸įä»ħåı¯ä»¥
    -0.10
    ä¸įä»ħèĥ½
    -0.10
    ä¸įä»ħæĺ¯
    -0.10
    ä¸įåıªæĺ¯
    -0.09
    ÑĢай
    -0.09
    èĻ½çĦ¶
    -0.09
    æŃª
    -0.09
    ä¸įä½Ĩ
    -0.09
    POSITIVE LOGITS
    åIJĮæĻĤãģ«
    0.13
     ëıĻìĭľìĹIJ
    0.13
    ä¹Łæľīå¾Īå¤ļ
    0.12
    åIJĮæŶ
    0.10
    åıĪæľī
    0.10
    åĽļ
    0.10
    çļĦåIJĮæŶ
    0.10
    åıĪæĺ¯
    0.09
    åIJĮæĹ¶ä¹Łæĺ¯
    0.09
    åIJĮæĻĤ
    0.09
    Activations Density 0.106%

    No Known Activations