© 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. 64041
    Prev
    Next
    INDEX
    Explanations

    good chance

    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
    æľīä½ķ
    -0.10
    neas
    -0.10
    æľīäºĨ
    -0.10
     previously
    -0.09
    usc
    -0.09
    æľĢæľī
    -0.09
    太太
    -0.08
    åIJŃ
    -0.08
    亲æīĭ
    -0.08
     ÑĢанее
    -0.08
    POSITIVE LOGITS
    çļĦä¸ĢéĿ¢
    0.10
    è¿Ļä¹Ī说
    0.10
     <<<
    0.10
    人们对
    0.10
    çļĦå£°éŁ³
    0.10
    è¿Ļæĺ¯åĽłä¸º
    0.10
    è¿ĻéĩĮ
    0.09
    ä¹ĭ称
    0.09
    ErrorException
    0.09
    ADER
    0.09
    Activations Density 0.619%

    No Known Activations