© 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. 60627
    Prev
    Next
    INDEX
    Explanations

    Playnite

    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
    æľīè¿Ļæł·çļĦ
    -0.11
    éŨæĪ·ç½ijç«Ļ
    -0.11
    _REUSE
    -0.10
    æĢµ
    -0.09
    ecs
    -0.09
    erde
    -0.09
    èĹģ
    -0.09
    驯
    -0.09
    bum
    -0.09
    è¿ĩåħ³
    -0.09
    POSITIVE LOGITS
    èĩĥ
    0.11
    ä¸įèĪį
    0.08
    æĺ¼
    0.08
    èĨĺ
    0.08
    ters
    0.08
    anza
    0.08
    çłį
    0.08
    PointSize
    0.08
    izable
    0.08
    åIJĥå¾Ĺ
    0.08
    Activations Density 0.129%

    No Known Activations