© 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. 36579
    Prev
    Next
    INDEX
    Explanations

    Names followed by more text

    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
    æ¬
    -0.09
    aday
    -0.08
    ike
    -0.08
    .sorted
    -0.08
    oded
    -0.08
    åģļä¸ĢäºĽ
    -0.08
    çħ
    -0.08
    è¨Ĺ
    -0.08
    é¦
    -0.08
    .Collectors
    -0.08
    POSITIVE LOGITS
    ç½ij讯
    0.10
    æĮĩçļĦæĺ¯
    0.09
    ä¸Ģ缴æĺ¯
    0.09
    æĺ¯çĶ±
    0.09
    æĺ¯æĮĩ
    0.09
    æĴ¼
    0.09
    åIJĮæĹ¶ä¹Ł
    0.09
    ãģ®ãģ¯
    0.08
    å°±æĦıåij³çĿĢ
    0.08
    ä¹Łå¥½
    0.08
    Activations Density 0.435%

    No Known Activations