© 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. 32505
    Prev
    Next
    INDEX
    Explanations

    we as customers or artists

    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
    éĵį
    -0.09
    ä»İä¸Ń
    -0.09
    utow
    -0.08
    满äºĨ
    -0.08
    åĽłèĢĮ
    -0.08
    asan
    -0.08
    æł·åŃIJ
    -0.08
     полов
    -0.08
    ãĥĭãĥ¼
    -0.08
    idor
    -0.08
    POSITIVE LOGITS
    亲èĩª
    0.09
    AndView
    0.09
    常说
    0.08
    èĬľ
    0.08
    常çĶ¨çļĦ
    0.08
    è¢ĸ
    0.08
    常çĶ¨
    0.08
    èĩªèIJ¥
    0.08
    /includes
    0.08
    æݨ广åºĶçĶ¨
    0.08
    Activations Density 0.042%

    No Known Activations