© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7741
    Prev
    Next
    INDEX
    Explanations

    matting, tablecloths, napkins

    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
    quete
    -0.10
    å°¼äºļ
    -0.09
    åĪ°çİ°åľ¨
    -0.09
    _UC
    -0.09
    çŃ¹å»º
    -0.08
    éªĪ
    -0.08
    zá
    -0.08
    _masks
    -0.08
    æĺ¥å¤ı
    -0.08
    erc
    -0.08
    POSITIVE LOGITS
    ä¸Ĭæľī
    0.10
    é¤IJæ¡Į
    0.10
    æĦıå¤ĸ
    0.09
    çģµ
    0.09
    æĦł
    0.09
    樨
    0.09
    åħ°
    0.08
     Ott
    0.08
    åĬŁåĬĽ
    0.08
    溱
    0.08
    Activations Density 0.010%

    No Known Activations