© 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. 61021
    Prev
    Next
    INDEX
    Explanations

    medicinal plants and their extracts

    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
    åģĥ
    -0.10
    ihan
    -0.10
    è°¨
    -0.10
    ondon
    -0.09
    URN
    -0.09
    å¼Ĥåľ°
    -0.09
    ÑĢаÐ
    -0.09
    ayer
    -0.09
    æµģè¡Į
    -0.09
    gay
    -0.09
    POSITIVE LOGITS
    æį®æĬ¥éģĵ
    0.09
    hung
    0.08
    æĪijçĪ¸
    0.08
    rd
    0.08
    ä¸ĢåŃĹ
    0.08
    å¹´æĬ¥
    0.08
    æ¦Ķ
    0.08
    éĢ¼
    0.08
    éľĵ
    0.08
    管å§Ķä¼ļ
    0.08
    Activations Density 0.026%

    No Known Activations