© 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. 37758
    Prev
    Next
    INDEX
    Explanations

    ovarian cancer

    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
    深深çļĦ
    -0.09
     dee
    -0.09
    æĹģ
    -0.09
     commissioned
    -0.09
    æ·±åħ¥
    -0.09
    _UNSIGNED
    -0.09
    ä¹ĭæīĢ以
    -0.09
    unar
    -0.09
    æ¸ĹéĢı
    -0.09
    è´¯éĢļ
    -0.09
    POSITIVE LOGITS
    åįµå·¢
    0.11
     ovar
    0.11
    å§IJ妹
    0.10
    å°ij女
    0.09
     ovarian
    0.09
    鸡汤
    0.09
    å§Ĭ妹
    0.09
    æ¹Ħ
    0.09
     fal
    0.09
    她们
    0.08
    Activations Density 0.322%

    No Known Activations