© 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. 577
    Prev
    Next
    INDEX
    Explanations

    empowerment

    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
    ÑĥÑĩ
    -0.09
    ÑĥÑĩа
    -0.09
    èµĦæºIJéħįç½®
    -0.08
    ../../../
    -0.08
    outs
    -0.08
    è¿Ļè¯Ŀ
    -0.08
    yna
    -0.08
    book
    -0.08
    chy
    -0.08
    deo
    -0.08
    POSITIVE LOGITS
    MENT
    0.12
    ement
    0.12
    /disable
    0.11
    ãĥ¡ãĥ³ãĥĪ
    0.10
    åIJİèĢħ
    0.09
    iveness
    0.09
    ingles
    0.09
    ioned
    0.09
    éĤ£å°±
    0.09
    idy
    0.09
    Activations Density 0.006%

    No Known Activations