© 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. 27046
    Prev
    Next
    INDEX
    Explanations

    countries and markets

    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
    好人
    -0.09
     REPL
    -0.09
    /vendor
    -0.09
    .datab
    -0.09
    industry
    -0.09
    çĹ´
    -0.08
    迳
    -0.08
    éĢļå¾Ģ
    -0.08
    çļĦæĹ¶ä»£
    -0.08
    常è¯Ĩ
    -0.08
    POSITIVE LOGITS
    å¸ĤåľºçļĦ
    0.11
    å¸ĤåľºéľĢæ±Ĥ
    0.10
    å¸Ĥåľº
    0.09
     markets
    0.09
    æī©å¼ł
    0.09
    ä¸¤åľ°
    0.09
    é»İ
    0.09
    èĭĽ
    0.09
    Çģ
    0.08
    æĺ¯ä»ĸ
    0.08
    Activations Density 0.082%

    No Known Activations