© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8293
    Prev
    Next
    INDEX
    Explanations

    localization and chemical studies

    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
    æİī
    -0.10
    èĬĿ麻
    -0.10
    _fit
    -0.09
    å®ī康
    -0.09
    è¡Ģ液
    -0.09
    åIJĦä½į
    -0.09
    æĹłçŁ¥
    -0.09
    ç¥Ń
    -0.08
    å¾ĹäºĨ
    -0.08
    èĭ±æīį
    -0.08
    POSITIVE LOGITS
    红æĺŁ
    0.10
    è½
    0.09
    DSP
    0.09
     dap
    0.09
    æ¯ıéļĶ
    0.09
    RICS
    0.09
    .SDK
    0.08
    çļĦå®ŀåĬĽ
    0.08
    è´Łæĭħ
    0.08
    æį£
    0.08
    Activations Density 1.914%

    No Known Activations