© 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. 26654
    Prev
    Next
    INDEX
    Explanations

    akin to

    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
    zelf
    -0.09
    åĪ¥ãģ®
    -0.09
    辩è¯ģ
    -0.09
    uding
    -0.08
    eri
    -0.08
    ä¸įçŁ¥éģĵ
    -0.08
    ovich
    -0.08
    ç«ĭæ¡Ī
    -0.08
    çī¹åĪ«
    -0.08
    æĽ·
    -0.08
    POSITIVE LOGITS
    ibri
    0.10
    ç»ıèIJ¥èĮĥåĽ´
    0.10
    æĪIJé¾Ļ
    0.09
    å°±æĺ¯ä¸Ģ个
    0.09
     unw
    0.09
    ãĥ¬ãĤ¹ãĥĪ
    0.09
    MediaType
    0.08
    .Pos
    0.08
    ç®ĹäºĨ
    0.08
    侥幸
    0.08
    Activations Density 0.005%

    No Known Activations