© 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. 34523
    Prev
    Next
    INDEX
    Explanations

    ex

    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
    edList
    -0.09
    ancing
    -0.09
     sexes
    -0.09
    eds
    -0.09
    compass
    -0.09
    Ñĥд
    -0.09
    鼶è·Ŀ离
    -0.09
    èħĭ
    -0.09
    лоÑĤ
    -0.09
    æºĸ
    -0.09
    POSITIVE LOGITS
    ç´§å¼ł
    0.09
    åįłçĶ¨
    0.09
    åĮ»ç§ij大åѦ
    0.08
    大åѦæ¯ķä¸ļ
    0.08
    umont
    0.08
    åıĤåĬłä¼ļè®®
    0.08
    ä¾Ŀ
    0.08
    æĸĹå¿Ĺ
    0.08
    ë¡ľìĦľ
    0.08
     tensions
    0.08
    Activations Density 0.033%

    No Known Activations