© 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. 30915
    Prev
    Next
    INDEX
    Explanations

    organic acids and amino acids

    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
    sed
    -0.09
    ä¹ł
    -0.08
     Cant
    -0.08
    æļ´
    -0.08
     sed
    -0.08
    帽åŃIJ
    -0.08
     tester
    -0.08
    .scheduler
    -0.08
    .script
    -0.08
    imony
    -0.08
    POSITIVE LOGITS
    æ°¨éħ¸
    0.10
    Ø´ÙĪ
    0.09
    çİĩè¾¾
    0.09
    æĢģ
    0.09
    argin
    0.09
    è¿ĽåŁİ
    0.09
    缺éĻ·
    0.09
    饮水
    0.09
    诱
    0.09
    èĥª
    0.09
    Activations Density 0.582%

    No Known Activations