© 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. 64132
    Prev
    Next
    INDEX
    Explanations

    comes an

    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
    æľ¬è´¨ä¸Ĭ
    -0.09
    è¿Ļæł·ä¸ĢæĿ¥
    -0.09
    åĩºçĶŁ
    -0.09
    ilet
    -0.09
    .eye
    -0.09
    寺
    -0.09
    inus
    -0.09
    æĶ¾çľ¼
    -0.09
    建åħļ
    -0.08
    ãģķãģ¦
    -0.08
    POSITIVE LOGITS
     Rubio
    0.11
    dain
    0.09
     возможноÑģÑĤÑĮ
    0.09
    ä¼ļ对
    0.09
    éĢģå¾Ģ
    0.09
    ä»ĸ对
    0.08
    exo
    0.08
    _tp
    0.08
    éĤ£ç§į
    0.08
    鸥
    0.08
    Activations Density 0.015%

    No Known Activations