© 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. 47924
    Prev
    Next
    INDEX
    Explanations

    for a duration

    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
    æıIJæĹ©
    -0.11
     ÙĦÙħدة
    -0.10
    åģļèµ·
    -0.10
    bjerg
    -0.10
    rad
    -0.09
    çĮ©
    -0.09
    èĵī
    -0.09
    ä¸įä¸Ĭ
    -0.09
    è¡Ķ
    -0.09
    æĮīæŶ
    -0.09
    POSITIVE LOGITS
    缸å½ĵ
    0.10
    asers
    0.09
    è¿Ļä¹Īå¤ļ
    0.09
    åĬ¿
    0.08
    å¤ļå°ij
    0.08
    æĽ´å¤ļ
    0.08
    足
    0.08
    å¼ĢèĬ±
    0.08
     ÙĨØŃÙĪ
    0.08
    èĭ¥å¹²
    0.07
    Activations Density 0.057%

    No Known Activations