© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10580
    Prev
    Next
    INDEX
    Explanations

    African American figures and institutions

    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
    çļĦå®ŀéĻħ
    -0.08
    สาย
    -0.08
    ç»Ħç»ĩå®ŀæĸ½
    -0.08
    æĻĶ
    -0.08
    æ»Ł
    -0.08
     занÑıÑĤ
    -0.08
     Actual
    -0.08
     insanların
    -0.08
    浪
    -0.08
    æīij
    -0.07
    POSITIVE LOGITS
    é»ijé¾Ļ
    0.12
    é»ij马
    0.10
    LOPT
    0.09
    thal
    0.09
    é»
    0.09
     GHC
    0.09
     BDS
    0.08
    蹬
    0.08
    _YUV
    0.08
    é»ij
    0.08
    Activations Density 0.069%

    No Known Activations