© 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. 27616
    Prev
    Next
    INDEX
    Explanations

    lessons and learning from experience

    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
    ç¦ıéŁ³
    -0.09
    -scripts
    -0.08
    Öħ
    -0.08
    åģļåĪ°
    -0.08
    lic
    -0.08
    æŁ¥çľĭæĽ´å¤ļ
    -0.08
    ä¸ŃåİŁ
    -0.08
     lodged
    -0.08
    å¸Ŀ
    -0.08
    é¼ĵ
    -0.08
    POSITIVE LOGITS
    GEST
    0.09
    ä¸ĭæĿ¥çļĦ
    0.09
    ä¸įåĩºæĿ¥
    0.09
    æĿ¥èĩªäºİ
    0.09
    æĿ²
    0.09
    казан
    0.09
    à¸Īาà¸ģà¸ģาร
    0.09
    нÑĤ
    0.09
    妻
    0.08
    cul
    0.08
    Activations Density 0.035%

    No Known Activations