© 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. 23120
    Prev
    Next
    INDEX
    Explanations

    ordering of two or three

    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
    姹
    -0.10
    ä¸Ģåij³
    -0.10
    ningen
    -0.09
    ä»»ä½ķå½¢å¼ı
    -0.09
    éĢĤåIJĪèĩªå·±
    -0.09
    渤海
    -0.09
    ги
    -0.09
    ahoo
    -0.09
    ä¸Ģåı·
    -0.09
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.09
    POSITIVE LOGITS
    两大
    0.12
     respectively
    0.10
    åĪĨåĪ«æĺ¯
    0.09
    åĪĨåĪ¥
    0.09
    åĪĨåĪ«ä¸º
    0.09
    两项
    0.09
    两类
    0.08
    åĪĨåĪ«
    0.08
    è¿Ļ两个
    0.08
    çļĦä¸įåIJĮ
    0.08
    Activations Density 0.086%

    No Known Activations