© 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. 2291
    Prev
    Next
    INDEX
    Explanations

    acupuncture, therapy, optometry

    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
    æįŁ
    -0.09
    itarian
    -0.09
    æķŀ
    -0.09
    -0.09
     пÑĢид
    -0.09
    çĦ¶æĺ¯
    -0.09
    æ·ĺ
    -0.08
    æIJŃ
    -0.08
     ×ij׼
    -0.08
    æ½®
    -0.08
    POSITIVE LOGITS
    åħ´å»º
    0.09
    .datetime
    0.08
    yped
    0.08
    æĮīæij©
    0.08
    ÃŃ
    0.08
    è¹ī
    0.08
    iven
    0.08
    ä¸İåħ¶ä»ĸ
    0.08
    åIJĮä»ģ
    0.08
    æĿĪ
    0.08
    Activations Density 0.010%

    No Known Activations