© 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. 18409
    Prev
    Next
    INDEX
    Explanations

    said after punctuation

    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
    éħ£
    -0.09
    åŀĴ
    -0.08
    èĩªçĦ¶æĺ¯
    -0.08
    çļĦä¸ĢåĪĩ
    -0.08
     rev
    -0.07
    æ²³æµģåŁŁ
    -0.07
    çݯç»ķ
    -0.07
    /or
    -0.07
    æĪIJè´¥
    -0.07
    è²Į
    -0.07
    POSITIVE LOGITS
    ÑijÑĤ
    0.10
    ploy
    0.09
    imet
    0.09
     Tiên
    0.09
    åĵī
    0.09
    меÑĢ
    0.09
    å·¥ä½ľæľºåĪ¶
    0.09
    .Inject
    0.09
     nonatomic
    0.09
    дÑĢ
    0.09
    Activations Density 0.026%

    No Known Activations