© 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. 9250
    Prev
    Next
    INDEX
    Explanations

    fee charge cost

    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
    ðĿĵ
    -0.10
    æīĭä¸ŃçļĦ
    -0.09
    ãĤīãģĽ
    -0.09
    cord
    -0.09
    ÙĥÙģ
    -0.09
    porn
    -0.09
    ÑĢок
    -0.09
    Ħ件
    -0.09
    à¹Ģà¸ĸ
    -0.09
    ApiClient
    -0.08
    POSITIVE LOGITS
    ç³ľ
    0.09
    çĦī
    0.08
    飧æĢ§
    0.08
    ä¸įèĤ¯
    0.08
    è§Ĵ度çľĭ
    0.08
    仲
    0.08
    ä¸İä¼Ĺä¸įåIJĮ
    0.08
    å·¨
    0.08
    éĿ¡
    0.08
    Çİ
    0.08
    Activations Density 0.026%

    No Known Activations