© 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. 32839
    Prev
    Next
    INDEX
    Explanations

    at least

    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
    Ñħо
    -0.10
    ä¸įåIJĪ
    -0.09
    åĢ¼çıŃ
    -0.09
    æĮº
    -0.08
    éĩijçīĮ
    -0.08
     parça
    -0.08
    .capacity
    -0.08
    è·µ
    -0.08
     cabo
    -0.08
     gradu
    -0.08
    POSITIVE LOGITS
    èĩ³å°ij
    0.17
    ä¸įå°ijäºİ
    0.13
    ä¸įä½İäºİ
    0.13
    ä»»ä½ķå½¢å¼ı
    0.12
    èµ·çłģ
    0.11
     ÑħоÑĤÑı
    0.11
    æľīè¶³å¤ŁçļĦ
    0.10
     atleast
    0.10
    æŁIJç§į
    0.10
    è¦ģä¹Ī
    0.10
    Activations Density 0.141%

    No Known Activations