© 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. 6036
    Prev
    Next
    INDEX
    Explanations

    i wish I could

    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
    尤为
    -0.09
    éŀŃ
    -0.09
    outh
    -0.08
    å¥ı
    -0.08
     Goose
    -0.08
    ä¹Łæĺ¯
    -0.08
    ä¹ŁæŃ£æĺ¯
    -0.08
    æģ»
    -0.08
    åħ³åı£
    -0.08
    åĩłä¹İæĺ¯
    -0.08
    POSITIVE LOGITS
    èĥ½åľ¨
    0.11
    说è¿ĩ
    0.10
    èĥ½æĬĬ
    0.10
     hasNext
    0.10
    é«
    0.09
    èĥ½å¾ĹåĪ°
    0.09
    клÑİÑĩи
    0.09
    æĽ´å¤ļçļĦ
    0.09
    åĥı个
    0.09
    æĽ´å¥½çļĦ
    0.09
    Activations Density 0.021%

    No Known Activations