© 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. 5536
    Prev
    Next
    INDEX
    Explanations

    about the author

    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
    tit
    -0.09
    å¼Ń
    -0.09
    pon
    -0.08
    表çݰ为
    -0.08
    诸
    -0.08
     pare
    -0.08
    çİĩè¾¾
    -0.08
    èĩªå®¶
    -0.08
    åĪ«äººçļĦ
    -0.08
    èĮĦ
    -0.08
    POSITIVE LOGITS
    äºĨè§£æĽ´å¤ļ
    0.10
    ä¸Ģè´¯
    0.10
    .getChannel
    0.09
    æľįåĬ¡ä¸Ńå¿ĥ
    0.09
    ä»ĸæĺ¯
    0.09
    æ¸Ĭ
    0.09
    å±¹
    0.09
    кÑĢаÑĤ
    0.09
    ério
    0.09
    å®ŀåĬĽ
    0.08
    Activations Density 0.031%

    No Known Activations