© 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. 31200
    Prev
    Next
    INDEX
    Explanations

    Eminem's daughter

    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
    èĨĬ
    -0.10
    æİ£
    -0.10
    åĿıäºĭ
    -0.09
    æİĮ
    -0.09
    ç¾İçļĦ
    -0.09
    ä½ļ
    -0.09
    åºĬ
    -0.09
    åľ¹
    -0.09
    çݯèĬĤ
    -0.09
    京åŁİ
    -0.08
    POSITIVE LOGITS
    æĶĴ
    0.10
    ä¸Ĭç½ij
    0.09
    aises
    0.09
    ä¸ĢæĹ¥
    0.09
    èĴ¿
    0.08
     dom
    0.08
    pra
    0.08
    readOnly
    0.08
    éĵ®
    0.08
    pus
    0.08
    Activations Density 0.066%

    No Known Activations