© 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. 2466
    Prev
    Next
    INDEX
    Explanations

    Pharrell Williams, Daniel Radcliffe

    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
    è¿ĻæĿ¡è·¯
    -0.11
    ä¸įéĹ´
    -0.09
    累累
    -0.09
    被åĬ¨
    -0.09
     deg
    -0.09
    æĮīè§Ħå®ļ
    -0.08
     comforts
    -0.08
     Snapshot
    -0.08
    çĤ¹å¤ļ
    -0.08
    èģĶ
    -0.08
    POSITIVE LOGITS
    æĥº
    0.09
     pé
    0.09
    éļ¼
    0.08
    å¼ķ
    0.08
    lon
    0.08
    emo
    0.08
    èįĨå·ŀ
    0.08
    åIJİç»Ń
    0.08
    é»ij马
    0.08
    ány
    0.08
    Activations Density 0.022%

    No Known Activations