© 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. 58965
    Prev
    Next
    INDEX
    Explanations

    on board, game, favour, thrown, enthusiastic

    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
    绯
    -0.10
    æĪIJåIJį
    -0.09
    修身
    -0.09
    ç±į
    -0.09
    ä¿®åħ»
    -0.09
    ç©°
    -0.09
    olin
    -0.09
    è¯Ħä¼°
    -0.08
    (DE
    -0.08
    èĩ»
    -0.08
    POSITIVE LOGITS
    积æŀģæĢ§
    0.11
    æĭ¥æĬ¤
    0.10
    çļĦ积æŀģæĢ§
    0.10
     ủng
    0.10
    åŁĿ
    0.10
    积æŀģéħįåIJĪ
    0.10
     tiên
    0.09
    æĶ¯æĮģ
    0.09
    积æŀģåĵįåºĶ
    0.09
    é¼ĵ
    0.09
    Activations Density 0.039%

    No Known Activations