© 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. 59199
    Prev
    Next
    INDEX
    Explanations

    cutting edge

    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
    éģ¥
    -0.09
    级以ä¸Ĭ
    -0.09
    æľªæĿ¥çļĦ
    -0.08
    èĮī
    -0.08
    æĹ©æľŁ
    -0.08
    tail
    -0.08
    éĺ³åı°
    -0.08
     recent
    -0.08
    天涯
    -0.08
    æĸ°åĮº
    -0.08
    POSITIVE LOGITS
    人们对
    0.10
     ürünü
    0.09
    åijĪ
    0.09
    è¿ŀäºij
    0.09
    /power
    0.09
    mPid
    0.09
    åĭĩäºİ
    0.09
    еÑĩно
    0.09
    expo
    0.08
    形象
    0.08
    Activations Density 0.014%

    No Known Activations