© 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. 10921
    Prev
    Next
    INDEX
    Explanations

    San Antonio

    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
    åįĹå±±
    -0.10
    stin
    -0.10
    ../../../
    -0.10
    è¾İ
    -0.09
    æ¯ĶåĪ©
    -0.09
    åŃº
    -0.09
    é¹
    -0.09
    åĵģä½į
    -0.09
    æŃ¥æŃ¥
    -0.09
    å¹£
    -0.08
    POSITIVE LOGITS
     Riy
    0.11
    oley
    0.09
    寡
    0.09
    è²Į
    0.09
    oire
    0.09
    изм
    0.08
    æĭ¬
    0.08
    åı¤äºº
    0.08
    esco
    0.08
    asion
    0.08
    Activations Density 0.010%

    No Known Activations