© 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. 2358
    Prev
    Next
    INDEX
    Explanations

    close contests and margins

    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
    мÑı
    -0.09
    ulet
    -0.08
    åIJŁ
    -0.08
    ç³ĸæŀľ
    -0.08
     Facts
    -0.08
    facts
    -0.08
    пиÑĤ
    -0.08
    .alpha
    -0.08
    conditionally
    -0.08
     facts
    -0.08
    POSITIVE LOGITS
    纷
    0.10
     margins
    0.10
    ä¹ĭäºī
    0.10
    精彩çļĦ
    0.10
    æ¿ĢåĬ±
    0.10
    çļĦç«ŀäºī
    0.09
    ç»ĵ
    0.09
    åıĮè¾¹
    0.09
    å·®è·Ŀ
    0.09
    ä¹ĭæĪĺ
    0.09
    Activations Density 0.088%

    No Known Activations