© 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. 20818
    Prev
    Next
    INDEX
    Explanations

    currency names and symbols

    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
    èĤ¢
    -0.10
    ä¸İæŶ
    -0.09
    稷
    -0.09
    èĬ¥
    -0.09
    æĬĬæīĭ
    -0.09
    ä»»æľŁ
    -0.09
    åĴ
    -0.09
    èĢĺ
    -0.09
    èįł
    -0.08
    TES
    -0.08
    POSITIVE LOGITS
    æĹĹ
    0.10
    à¸ļาà¸Ĺ
    0.09
    รา
    0.09
    ç®±
    0.09
    åĿĹéĴ±
    0.08
    ë¶Ī
    0.08
     Cent
    0.08
    æ¯ģ
    0.08
    istes
    0.08
    ä¸ĢåĪĨéĴ±
    0.08
    Activations Density 0.038%

    No Known Activations