© 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. 27631
    Prev
    Next
    INDEX
    Explanations

    home or back

    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
    ç½ijçIJĥ
    -0.11
    ä¹ĵ
    -0.09
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.08
    bis
    -0.08
    imators
    -0.08
    emic
    -0.08
     åķ
    -0.08
    ç½®æį¢
    -0.08
    ä¹ĭæĺŁ
    -0.08
    åįķä¸Ģ
    -0.08
    POSITIVE LOGITS
    çļĦæĺ¯
    0.10
    eries
    0.10
    大åŁİå¸Ĥ
    0.10
    主ä½ĵ责任
    0.09
     Sous
    0.08
    èį£èªī
    0.08
    ä»Ģä¹Īæł·çļĦ
    0.08
    CTS
    0.08
    ä¸ĢæĬĬ
    0.08
    责任
    0.08
    Activations Density 0.008%

    No Known Activations