© 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. 18720
    Prev
    Next
    INDEX
    Explanations

    museums and education

    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
    å®Įç¾İ
    -0.08
    illum
    -0.08
    æŶä¸įæŶ
    -0.08
    éŃī
    -0.08
    æĮĸæİĺ
    -0.08
    ëĦ·
    -0.08
     krat
    -0.08
     Ker
    -0.07
    èįª
    -0.07
    itable
    -0.07
    POSITIVE LOGITS
    家乡
    0.11
    çļĦä¸įåIJĮ
    0.10
    æĥ³åĬŀæ³ķ
    0.10
    okie
    0.09
    ä¸įåIJĮçļĦ
    0.09
    ÑĭваÑĤÑĮ
    0.09
    .blob
    0.09
    ä¹ŀ
    0.09
    çļĦæ¨¡æł·
    0.08
    课æĸĩ
    0.08
    Activations Density 0.097%

    No Known Activations