© 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. 50155
    Prev
    Next
    INDEX
    Explanations

    National Register of Historic Places

    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
    fi
    -0.09
    ä¿Ŀåģ¥
    -0.09
     thiên
    -0.09
    æIJŀ好
    -0.09
    çįł
    -0.08
    ç¼¢
    -0.08
    ç»Ŀ对
    -0.08
    確ä¿Ŀ
    -0.08
     manip
    -0.08
    åįļçī©
    -0.08
    POSITIVE LOGITS
    æ³¼
    0.10
    ä¸Ģæī¹
    0.09
    oreach
    0.09
    æĤ£
    0.08
    äºŃ
    0.08
    ably
    0.08
    æĿijåħļæĶ¯éĥ¨
    0.08
    çļĦé«ĺ度
    0.08
    ulan
    0.08
    建çŃijæĿIJæĸĻ
    0.08
    Activations Density 0.052%

    No Known Activations