© 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. 54406
    Prev
    Next
    INDEX
    Explanations

    incorporated by reference herein

    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
     vo
    -0.09
    даÑĢ
    -0.09
    çį¾
    -0.08
     civil
    -0.08
    éĴĬ
    -0.08
     gall
    -0.08
    .usage
    -0.08
    дол
    -0.08
    æ£ł
    -0.08
    大å¤ļæķ°äºº
    -0.08
    POSITIVE LOGITS
    åįģåŃĹ
    0.09
    ç²¾åįİ
    0.09
    è¿ĽæĿ¥
    0.09
    ä¸ŃéĢĶ
    0.09
    åħħå®ŀ
    0.09
    imd
    0.09
    åĽŀ头
    0.09
    æĬ¬å¤´
    0.08
     Programmer
    0.08
    vue
    0.08
    Activations Density 0.107%

    No Known Activations