© 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. 39175
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

    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
    åĩłä¸ª
    -0.10
    èĭ¥å¹²
    -0.10
    两ç§į
    -0.10
    两类
    -0.10
     hundreds
    -0.10
     two
    -0.10
    æĹłæķ°
    -0.10
    åįģåĩłä¸ª
    -0.10
    两家
    -0.09
    两级
    -0.09
    POSITIVE LOGITS
    å¾Ī满æĦı
    0.10
    èĥŀ
    0.09
    enda
    0.09
    æ¾Ħ
    0.09
    legalArgumentException
    0.09
    ago
    0.09
    æħ¨
    0.09
    ä¸įåIJĮçļĦ
    0.09
    éī´åĪ«
    0.08
    -piece
    0.08
    Activations Density 0.182%

    No Known Activations