© 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. 24017
    Prev
    Next
    INDEX
    Explanations

    Prohibition era

    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
     batt
    -0.10
    ãģĸ
    -0.09
    åĬª
    -0.09
    è°ı
    -0.09
    è®®
    -0.09
    æ¸Į
    -0.09
    æ½ŀ
    -0.09
    çļĦè¡£æľį
    -0.09
    é¦Ĭ
    -0.09
    ë£Į
    -0.09
    POSITIVE LOGITS
    è´ª
    0.10
    è¦ģ害
    0.09
    çĽ
    0.09
    ÑģÑĤи
    0.08
    éĽĩ
    0.08
    çļĦæĵįä½ľ
    0.08
    ä¸ĢæŶ
    0.08
    çݰ代çī©æµģ
    0.08
    æĴ¬
    0.08
    éĴ±
    0.08
    Activations Density 0.111%

    No Known Activations