© 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. 31578
    Prev
    Next
    INDEX
    Explanations

    diversity and spiritual values

    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
    pras
    -0.10
    示æĦı
    -0.09
     extras
    -0.09
    èijŃ
    -0.08
    çĦ
    -0.08
    讪
    -0.08
     concession
    -0.08
    ä¸İä¼Ĺä¸įåIJĮ
    -0.08
    éĵģ
    -0.08
    archs
    -0.08
    POSITIVE LOGITS
    èĩªçĦ¶èµĦæºIJ
    0.10
    ç§įåŃIJ
    0.10
    骤
    0.09
    клÑİÑĩа
    0.09
    纳
    0.09
    OrElse
    0.09
    éļı便
    0.09
    ä¸Ģç¬Ķ
    0.09
    æĦļèł¢
    0.09
     Natur
    0.08
    Activations Density 0.101%

    No Known Activations