© 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. 27534
    Prev
    Next
    INDEX
    Explanations

    28 receptions

    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
    è¿Ļ件äºĭæĥħ
    -0.10
    IME
    -0.10
    åįĬ天
    -0.09
    æªĦ
    -0.09
    ICI
    -0.09
    梨
    -0.09
    åķIJ
    -0.08
    åķĨæľº
    -0.08
    缼å¼Ģ
    -0.08
    ä¸ĢæĿ¡é¾Ļ
    -0.08
    POSITIVE LOGITS
    ød
    0.09
    åĨį次
    0.09
    utron
    0.08
    ÃĤN
    0.08
    _subs
    0.08
    ystem
    0.08
    uren
    0.08
    hana
    0.08
    æŃ¤æ¬¡
    0.08
    缮åīį
    0.07
    Activations Density 0.099%

    No Known Activations