© 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. 57881
    Prev
    Next
    INDEX
    Explanations

    he/she him/her pronouns

    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
    æľ¬èº«å°±
    -0.11
    åģıåģı
    -0.10
    让æĤ¨
    -0.10
    eing
    -0.10
    延ç»Ń
    -0.09
    æľ¬èº«å°±æĺ¯
    -0.09
     itself
    -0.09
    让人们
    -0.09
    让人
    -0.09
    æį£
    -0.09
    POSITIVE LOGITS
    æĦıåIJij
    0.08
    ichern
    0.08
     indian
    0.08
    åĭ¿
    0.08
    icher
    0.08
    åİ»è¿ĩ
    0.08
    æīĭä¸ŃçļĦ
    0.08
    iche
    0.08
    ä¸Ģèµ·åİ»
    0.08
    üns
    0.07
    Activations Density 0.039%

    No Known Activations