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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6596
    Prev
    Next
    INDEX
    Explanations

    converted to Islam or religion

    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
    ern
    -0.09
    窨
    -0.09
    æĶ¾æīĭ
    -0.09
    ä¸įåĩºæĿ¥
    -0.09
    æī©
    -0.08
    ardu
    -0.08
    rema
    -0.08
    ernes
    -0.08
    ä»ĭ
    -0.08
    strained
    -0.08
    POSITIVE LOGITS
    è¿ĩæĿ¥
    0.11
    转åIJij
    0.11
    åIJİçļĦ
    0.10
    å½Ĵ
    0.10
    åĬłåħ¥äºĨ
    0.09
    æѸ
    0.09
    转身
    0.09
    éģİä¾Ĩ
    0.09
    æĪIJ为
    0.09
    æĹĹä¸ĭçļĦ
    0.09
    Activations Density 0.041%

    No Known Activations