© 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. 6222
    Prev
    Next
    INDEX
    Explanations

    pass or fail a test

    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
    æijĺ
    -0.10
    Directions
    -0.09
    çĥ¬
    -0.09
    DCALL
    -0.09
    REEN
    -0.09
    обоÑĢ
    -0.09
    èĢĺ
    -0.09
    ÂŃtion
    -0.09
    è¿Ļåıª
    -0.09
     puss
    -0.09
    POSITIVE LOGITS
    èĢĥéªĮ
    0.14
    åıĹä¸įäºĨ
    0.11
     muster
    0.11
    åIJĪæł¼
    0.11
     tests
    0.11
    qua
    0.10
    åºķ线
    0.09
    icle
    0.09
     Tests
    0.09
    éĩįéĩį
    0.09
    Activations Density 0.062%

    No Known Activations