© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2043
    Prev
    Next
    INDEX
    Explanations

    prior to

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ëĿ¼ëıĦ
    -0.10
     scrollTop
    -0.08
    è¿Ļå°±æĺ¯
    -0.08
     ведÑĮ
    -0.08
    iker
    -0.08
    å¼Ħ
    -0.08
    Ñĥгл
    -0.08
    éĢĬ
    -0.08
     تÙħاÙħ
    -0.08
    æ¯ķç«Łæĺ¯
    -0.08
    POSITIVE LOGITS
    åŃļ
    0.09
     Burl
    0.09
    opus
    0.09
    rcode
    0.08
    ä»Ĭ天çļĦ
    0.08
     autop
    0.08
    主æµģ
    0.08
    atie
    0.08
    Strict
    0.08
    æ¼Ķ
    0.08
    Activations Density 0.038%

    No Known Activations