© 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. 24332
    Prev
    Next
    INDEX
    Explanations

    squad

    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
    ä¸Ģ对
    -0.10
    æĢ¥éĢŁ
    -0.10
    çıī
    -0.09
    åĬłåĪĨ
    -0.09
    _IMPL
    -0.09
    é¢Ĩ
    -0.09
    ç®ķ
    -0.09
    æľīä¸įåIJĮçļĦ
    -0.09
    å°ıçĻ½
    -0.09
    æĹłæīĢ
    -0.09
    POSITIVE LOGITS
    åIJįåįķ
    0.09
    å¤ĩæĪĺ
    0.09
    anger
    0.09
    elli
    0.08
    avad
    0.08
    人éĢī
    0.08
     flick
    0.08
    åİĦ
    0.08
    ÑĢев
    0.08
     Fif
    0.08
    Activations Density 0.037%

    No Known Activations