© 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. 28158
    Prev
    Next
    INDEX
    Explanations

    medical professionals and patients

    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
    åķĨ家
    -0.09
    å¸Ĥåħ¬å®īå±Ģ
    -0.09
    æŃĮåĶ±
    -0.09
    ä¸Ĭ课
    -0.08
     Ventura
    -0.08
    åĿ¤
    -0.08
    妩
    -0.08
    æŃĮè¯į
    -0.08
    éĹº
    -0.08
    å°ıåIJĥ
    -0.08
    POSITIVE LOGITS
     treatments
    0.10
    è¯Ĵ
    0.10
    éĻ¢éķ¿
    0.10
    ç»·
    0.10
    STD
    0.09
    æľįåĬ¡æ°´å¹³
    0.09
     treating
    0.09
    éĵį
    0.09
    漫
    0.09
    æľįåĬ¡è´¨éĩı
    0.09
    Activations Density 0.188%

    No Known Activations