© 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. 17164
    Prev
    Next
    INDEX
    Explanations

    lit. or literally followed by explanation

    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
    ç»ķ
    -0.09
    éĤ£æł·çļĦ
    -0.08
    åĢĵ
    -0.08
     resid
    -0.08
    èµĭ
    -0.08
    让人
    -0.08
    å©ī
    -0.08
    antal
    -0.08
     sal
    -0.08
    AME
    -0.07
    POSITIVE LOGITS
    è¿Ļåı¥è¯Ŀ
    0.10
    çļĦæĦıæĢĿ
    0.10
    è¿ĻéĩĮæĺ¯
    0.09
    è¿ĻéĩĮ
    0.09
    çIJı
    0.09
    çļĦ说æ³ķ
    0.08
    éĢĹ
    0.08
    endoza
    0.08
    æģĤ
    0.08
    鸷
    0.08
    Activations Density 0.019%

    No Known Activations