© 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. 17185
    Prev
    Next
    INDEX
    Explanations

    correspondence and official communication

    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
    寡
    -0.10
    æĬ¥éģĵ
    -0.09
    craft
    -0.09
     Concord
    -0.09
    à¹Ģà¸ī
    -0.09
    èĢģ人家
    -0.08
    orate
    -0.08
     Ùħجر
    -0.08
    ÑĤÑıж
    -0.08
    åīįèĢħ
    -0.08
    POSITIVE LOGITS
    欺
    0.09
    åŁºè°ĥ
    0.09
    æĺ¨æĹ¥
    0.09
    äºĨä¸Ģ份
    0.09
    ç»ĥ
    0.09
    æĺ¨å¤©
    0.09
    æıIJæĹ©
    0.09
    涵
    0.09
    çļĦæĸĩåŃĹ
    0.09
    çľ¼ä¸ĭ
    0.09
    Activations Density 0.057%

    No Known Activations