© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24103
    Prev
    Next
    INDEX
    Explanations

    network and connections

    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
    Negative Logits
    èĩªæľī
    -0.10
    æĶ¹åĪ¶
    -0.09
    ader
    -0.09
    ç¾Ĭæ¯Ľ
    -0.09
    ä¸ī项
    -0.09
    åĬ²
    -0.08
    åĭģ
    -0.08
    AGO
    -0.08
    士
    -0.08
    åĦ¿ç«¥
    -0.08
    POSITIVE LOGITS
    éģįå¸ĥ
    0.10
    ç½ijä¸Ĭ
    0.09
    è¨Ĺ
    0.09
    åĭī强
    0.09
    åľĪ
    0.09
    åĵ¨
    0.09
     ÑģеÑĤи
    0.08
    fs
    0.08
    çIJħ
    0.08
    æĿĥå¨ģ
    0.08
    Activations Density 0.020%

    No Known Activations