© 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. 3920
    Prev
    Next
    INDEX
    Explanations

    has/have/had followed by past participle

    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
    æĸ°å¼Ģ
    -0.09
    ÑģÑĮ
    -0.09
    /MPL
    -0.09
    ilers
    -0.09
    ç»ıéªĮ
    -0.08
    xAB
    -0.08
    ä¸Ģç³»åĪĹ
    -0.08
    ÑĤов
    -0.08
    ä¸Ģ座
    -0.08
    ä¸ĢäºĽ
    -0.08
    POSITIVE LOGITS
    æŶå°ļ
    0.11
    åºķå±Ĥ
    0.09
    俺
    0.09
    iani
    0.09
    åıĪ被
    0.09
    .proc
    0.08
    ita
    0.08
    å¯Ŀ
    0.08
    åı¯èĥ½å¯¼èĩ´
    0.08
    æĴ®
    0.08
    Activations Density 0.174%

    No Known Activations