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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8568
    Prev
    Next
    INDEX
    Explanations

    tuning in

    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
    çļĦçľ¼ç¥ŀ
    -0.10
    æĮīä¸ĭ
    -0.10
    æĢ»è§īå¾Ĺ
    -0.09
    -icons
    -0.09
    ÂŃi
    -0.09
    ÑģÑĤавка
    -0.09
    èµĻ
    -0.09
    .icons
    -0.09
    outine
    -0.09
    sst
    -0.09
    POSITIVE LOGITS
    à¹ĥ
    0.10
    è°Ł
    0.09
    anz
    0.08
    åľ¨ä¸Ĭæµ·
    0.08
     toolbox
    0.08
    æīĢèĩ´
    0.08
    å°ıå§ijå¨ĺ
    0.08
    æĥĺ
    0.08
    attering
    0.08
    DRV
    0.08
    Activations Density 0.001%

    No Known Activations