© 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. 63109
    Prev
    Next
    INDEX
    Explanations

    ironic or ironically

    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
    æķ£
    -0.09
    enn
    -0.09
    ÙĪÙĬ
    -0.08
    adier
    -0.08
    ой
    -0.08
    ival
    -0.08
    azed
    -0.08
    æIJª
    -0.07
    åģļçļĦ
    -0.07
    çħ¨
    -0.07
    POSITIVE LOGITS
    è°ij
    0.10
    亶
    0.09
    æ·ij
    0.09
    ron
    0.09
    è´¶
    0.09
    åĬ¬
    0.09
    黩
    0.09
    RON
    0.08
    ulous
    0.08
    ä¸įæĪIJ
    0.08
    Activations Density 0.004%

    No Known Activations