© 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. 59439
    Prev
    Next
    INDEX
    Explanations

    numeric codes and sequences

    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
    ä¹Łåıªæĺ¯
    -0.10
     Че
    -0.10
    æķķ
    -0.09
    å¨ģæħij
    -0.09
    etas
    -0.09
    FW
    -0.09
    æĹ¥æĬ¥ç¤¾
    -0.09
    OOT
    -0.09
    ocity
    -0.08
    sth
    -0.08
    POSITIVE LOGITS
    以æĿ¥
    0.09
    ISCO
    0.08
     penny
    0.08
    è¢Ĵ
    0.08
    7
    0.08
    è¿IJæ°Ķ
    0.08
    2
    0.08
    1
    0.08
    åĭĩäºİ
    0.08
    9
    0.08
    Activations Density 0.121%

    No Known Activations