© 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. 59270
    Prev
    Next
    INDEX
    Explanations

    highlight

    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
    scape
    -0.10
    ³
    -0.10
    liness
    -0.10
    uset
    -0.10
     NDP
    -0.10
    è¸ıå®ŀ
    -0.10
    çķĮçļĦ
    -0.09
    epar
    -0.09
    ubi
    -0.09
    antine
    -0.08
    POSITIVE LOGITS
    çĻ»åľº
    0.09
    ÑĢÑĭ
    0.09
    纷
    0.09
    oeff
    0.09
    ä¹ĭä½ľ
    0.09
    athers
    0.09
    é©°
    0.09
    æİ£
    0.08
    è¡«
    0.08
    ıy
    0.08
    Activations Density 0.013%

    No Known Activations