© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47395
    Prev
    Next
    INDEX
    Explanations

    books and bookstores

    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
    Negative Logits
    ç±³é¥Ń
    -0.11
    _license
    -0.10
    éĶ¦æłĩ
    -0.09
    ipes
    -0.09
    ober
    -0.09
    оÑĩки
    -0.09
    éĩijéĵ¶
    -0.09
    é£Łåĵģå®īåħ¨
    -0.09
    åĨ¢
    -0.09
    åIJĦ个æĸ¹éĿ¢
    -0.09
    POSITIVE LOGITS
    书åºĹ
    0.17
    书é¦Ļ
    0.15
     bookstore
    0.14
     reading
    0.14
    éĺħ读
    0.14
    读书
    0.14
    书ç±į
    0.14
    Reading
    0.12
    书
    0.12
     book
    0.12
    Activations Density 0.081%

    No Known Activations