© 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. 8997
    Prev
    Next
    INDEX
    Explanations

    vendor-specific features

    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
     instagram
    -0.08
    çıª
    -0.08
     Mess
    -0.07
    Berry
    -0.07
     Instagram
    -0.07
     Berry
    -0.07
    èĬĿ
    -0.07
    ÑĨев
    -0.07
    -click
    -0.07
    éĴ¤
    -0.07
    POSITIVE LOGITS
    venture
    0.09
    ç»Ļ大家
    0.08
    åıij
    0.08
    èµ°è¿ĩ
    0.08
    software
    0.08
    æݬ
    0.08
    说ä¸įåĩº
    0.08
    Software
    0.08
    æĿī
    0.08
    Specifier
    0.08
    Activations Density 0.252%

    No Known Activations