© 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. 18371
    Prev
    Next
    INDEX
    Explanations

    iPhone app

    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
    bourne
    -0.10
     tripod
    -0.09
    绥
    -0.08
    ÑģÑĤв
    -0.08
    ivil
    -0.08
    åıĺäºĨ
    -0.08
    让æ¶Īè´¹èĢħ
    -0.08
    æµ·å¤ĸå¸Ĥåľº
    -0.08
    æİ¥ç§į
    -0.08
    大纲
    -0.08
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.11
    lemen
    0.10
    åħļåĴĮ
    0.10
    å¼ıçļĦ
    0.09
    /flutter
    0.09
    å¼Ģåħĥ
    0.09
    æī«ä¸Ģæī«
    0.09
    uft
    0.09
    éķ¿å®ī
    0.09
    (iOS
    0.09
    Activations Density 0.106%

    No Known Activations