© 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. 47433
    Prev
    Next
    INDEX
    Explanations

    furnace construction

    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
    éªij
    -0.10
    stalk
    -0.09
    æ¼ł
    -0.09
    ç¢Ł
    -0.08
     бÑĥм
    -0.08
    ä½ľæ¡Ī
    -0.08
    8
    -0.08
    4
    -0.08
    é¨İ
    -0.08
    åķ®
    -0.08
    POSITIVE LOGITS
    å¼Ģéĩĩ
    0.11
    æĸ§
    0.11
    ç²¾
    0.10
    åĩ¿
    0.10
    è¿ĻåĿĹ
    0.10
    æĿIJ
    0.09
    建éĢł
    0.09
    argin
    0.09
    çłį
    0.09
    IRT
    0.09
    Activations Density 0.225%

    No Known Activations