© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8265
    Prev
    Next
    INDEX
    Explanations

    sports statistics and scores

    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
    åIJĦ个æĸ¹éĿ¢
    -0.11
    彪
    -0.09
    ä½°
    -0.09
    åĩłä½į
    -0.09
    /sources
    -0.09
    åIJĦ个çݯèĬĤ
    -0.09
    izzo
    -0.09
    èħ±
    -0.09
    大åĬĽæĶ¯æĮģ
    -0.08
    orge
    -0.08
    POSITIVE LOGITS
    çĶļèĩ³
    0.10
     bri
    0.09
    åĸ½
    0.09
    çĶļèĩ³è¿ŀ
    0.09
    ä¸İæŶ
    0.08
    æľīä¸Ģå®ļ
    0.08
    第ä¸ī次
    0.08
    ISE
    0.08
    ä¹ĥèĩ³
    0.08
    æĬĹæĪĺ
    0.08
    Activations Density 0.042%

    No Known Activations