© 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. 39928
    Prev
    Next
    INDEX
    Explanations

    make or made

    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
    åįı
    -0.10
    åĪ°åºķæĺ¯
    -0.10
    ä¸Ģ次
    -0.10
    åľ¨æĪijåĽ½
    -0.09
    atar
    -0.09
    è¶ģ
    -0.09
     Cov
    -0.09
     СейÑĩаÑģ
    -0.08
    WithError
    -0.08
    å·¥ä¼ļ
    -0.08
    POSITIVE LOGITS
    人们
    0.11
    éļ½
    0.09
    æīĢæľī人
    0.09
    使人
    0.09
    æīĢæľī人éĥ½
    0.09
    éĢ¼è¿ij
    0.09
    è¶Ĭè¿ĩ
    0.09
    人们对
    0.09
    大家éĥ½
    0.09
    大家
    0.09
    Activations Density 0.060%

    No Known Activations