© 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. 9621
    Prev
    Next
    INDEX
    Explanations

    CountyCourtCommissionBoard

    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
    æĪijçľģ
    -0.10
    åĽ½åĬ¡éĻ¢
    -0.09
    arent
    -0.09
    å¯ĵ
    -0.08
    (Frame
    -0.08
    uvw
    -0.08
    tiles
    -0.08
    é«ĺ楼
    -0.08
    ETO
    -0.08
    çļĦåŁİå¸Ĥ
    -0.08
    POSITIVE LOGITS
    çģ¯ç¬¼
    0.10
    åIJĦè¡Į
    0.09
    å·¡åĽŀ
    0.09
    ä¸įèµ·
    0.09
    贯彻
    0.09
    oard
    0.08
    åįİ缼
    0.08
    æľ¬æľĪ
    0.08
    ä¸Ģ楼
    0.08
    妨ç¢į
    0.08
    Activations Density 0.109%

    No Known Activations