© 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. 50299
    Prev
    Next
    INDEX
    Explanations

    age, mean, or height

    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
    èĤ¥
    -0.08
    ä¿Ŀæļĸ
    -0.08
    ä»ĺåĩº
    -0.08
    ULK
    -0.08
     Cran
    -0.08
    åŁºæľ¬
    -0.08
    ramid
    -0.08
    imit
    -0.07
     Formal
    -0.07
    _basic
    -0.07
    POSITIVE LOGITS
     ìł
    0.11
    çİij
    0.11
    æĺ¯ä¸Ģç§į
    0.09
    è°ĥæŁ¥æĺ¾ç¤º
    0.09
    irie
    0.09
    าย
    0.09
    ç¥ī
    0.09
    ELLOW
    0.08
     ÐłÐ¾ÑģÑģийÑģкой
    0.08
    è¿ĻåĦ¿
    0.08
    Activations Density 1.158%

    No Known Activations