© 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. 29600
    Prev
    Next
    INDEX
    Explanations

    retrospectively analyzed

    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
    é¢ĦåħĪ
    -0.10
    inston
    -0.10
    æıIJåīį
    -0.10
    .tabs
    -0.09
    æѤæŶ
    -0.09
    æ¶ħ
    -0.09
    yclopedia
    -0.08
    ä¸ĢæŶ
    -0.08
    Accessible
    -0.08
    lover
    -0.08
    POSITIVE LOGITS
    第ä¸Ģä½į
    0.09
    gers
    0.09
    ively
    0.09
    алÑĮно
    0.09
    ive
    0.09
    aneously
    0.08
    sembled
    0.08
    èĺij
    0.08
    为广大
    0.08
    ally
    0.08
    Activations Density 0.038%

    No Known Activations