© 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. 6274
    Prev
    Next
    INDEX
    Explanations

    by or via

    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
     вообÑīе
    -0.09
    íĸ¥
    -0.08
    æĿ¥
    -0.08
    ä¸ĬæĿ¥
    -0.08
     autres
    -0.08
    èµ·çĤ¹
    -0.08
    ä¸ĭéĿ¢å°±
    -0.08
    ç¿
    -0.08
    è¿Ļç±»
    -0.08
    æѤ类
    -0.08
    POSITIVE LOGITS
    éĿł
    0.12
     either
    0.11
    æĥ°
    0.11
    纽带
    0.11
    ä¸Ģå®ļçļĦ
    0.10
    åħ±åIJĮåĬªåĬĽ
    0.09
    oit
    0.09
    Either
    0.09
     virtue
    0.09
    åĨľä¸ļåĨľæĿij
    0.09
    Activations Density 0.352%

    No Known Activations