© 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. 695
    Prev
    Next
    INDEX
    Explanations

    outside or front of

    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
    riding
    -0.09
    æīĭ
    -0.09
    æĻļ
    -0.09
     اÙĦØ¥ÙĨ
    -0.09
    rijk
    -0.09
    ç¼
    -0.09
     Luz
    -0.09
    ÐŀÐĿ
    -0.09
    /live
    -0.09
    atra
    -0.09
    POSITIVE LOGITS
    éŨåīį
    0.16
    éŨåı£
    0.14
    éŨå¤ĸ
    0.13
     outside
    0.10
    åĽ½æĹĹ
    0.10
    æł¡å¤ĸ
    0.09
    家éŨåı£
    0.09
    éĻĦå±ŀ
    0.09
    post
    0.09
    ires
    0.08
    Activations Density 0.077%

    No Known Activations