© 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. 62663
    Prev
    Next
    INDEX
    Explanations

    home games

    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
    æŃ£å¸¸ä½¿çĶ¨
    -0.10
    à¹Īะ
    -0.10
    ä¸įåłª
    -0.09
    éļĺ
    -0.09
    ä¸Ģ个人
    -0.09
    顺
    -0.09
     Cup
    -0.09
    个人信æģ¯
    -0.08
    æģIJ
    -0.08
    å¾ĹäºĨ
    -0.08
    POSITIVE LOGITS
    è¾Ł
    0.09
    æĿ¡ä»¶ä¸ĭ
    0.09
    /manual
    0.09
    åģļå®Į
    0.09
    /original
    0.09
    æIJĢ
    0.09
    ç¼±
    0.09
    .getExternal
    0.08
    PLEX
    0.08
    æķijåij½
    0.08
    Activations Density 0.007%

    No Known Activations