© 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. 38898
    Prev
    Next
    INDEX
    Explanations

    beauty and attractiveness

    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
    esc
    -0.09
    大åħ¨
    -0.09
    æłĵ
    -0.09
    áĥ¬
    -0.09
    ä¹ŀ
    -0.09
    ette
    -0.08
     ÙĪبÙĬÙĨ
    -0.08
    ÑĮев
    -0.08
     ener
    -0.08
    rib
    -0.08
    POSITIVE LOGITS
    åij¨å²ģ
    0.11
    çļĦèĦ¸
    0.10
    容è²Į
    0.10
    å¸ħ
    0.10
    èģª
    0.09
    /angular
    0.09
    峤
    0.09
     shar
    0.09
    èĦ¸
    0.09
     ÙĪجÙĩ
    0.09
    Activations Density 0.030%

    No Known Activations