© 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. 4651
    Prev
    Next
    INDEX
    Explanations

    just a / only a

    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
    éªĦ
    -0.10
    æıŃæĻĵ
    -0.10
    grave
    -0.10
    å¼ı
    -0.09
    缴æİ¥
    -0.09
    icha
    -0.09
    æĥĨ
    -0.09
    edic
    -0.09
    æķŀ
    -0.09
    åijĽ
    -0.09
    POSITIVE LOGITS
    ä¸įè¿ĩæĺ¯
    0.13
    åıªä¸įè¿ĩæĺ¯
    0.12
    æĻ®éĢļçļĦ
    0.12
     mere
    0.12
    åıªæĺ¯ä¸Ģ个
    0.12
    æīĵå·¥
    0.10
    ä¸ĢåĽŀäºĭ
    0.10
    èĤ²
    0.09
    ordinary
    0.09
    ivo
    0.09
    Activations Density 0.052%

    No Known Activations