© 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. 31217
    Prev
    Next
    INDEX
    Explanations

    making or producing outcomes

    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
    çļĦä¸Ģ项
    -0.11
    çļĦä¸Ģ大
    -0.11
    è¿Ļå¼ł
    -0.11
    天天
    -0.10
    çļĦä¸Ģ个
    -0.10
    çļĦ身ä½ĵ
    -0.10
    à²Ł
    -0.10
    è¿Ļ件
    -0.09
    çļĦ家åºŃ
    -0.09
    çļĦæĸĩåĮĸ
    -0.09
    POSITIVE LOGITS
    åĬ¨äºº
    0.09
    æĸ°çļĦ
    0.09
    çĶµåŃIJä¿¡æģ¯
    0.08
    äºĭæĥħ
    0.08
    åħ´å¥ĭ
    0.07
    rens
    0.07
    è¿Ŀ
    0.07
     sym
    0.07
     different
    0.07
    éĤ¦
    0.07
    Activations Density 0.654%

    No Known Activations