© 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. 2460
    Prev
    Next
    INDEX
    Explanations

    in the world today

    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
    俾
    -0.10
    çī¯
    -0.10
    å¸ı
    -0.09
    ĵį
    -0.09
    寨
    -0.09
    èĭ´
    -0.09
    åĿĩåĮĢ
    -0.09
    ç«łç¨ĭ
    -0.09
    (er
    -0.08
    èĸ®
    -0.08
    POSITIVE LOGITS
    çݯå¢ĥä¸ĭ
    0.13
    æ¿ĢçĥĪçļĦ
    0.12
    å¤įæĿĤçļĦ
    0.12
    æ¿ĢçĥĪ
    0.10
    çݯå¢ĥä¸Ń
    0.09
     penn
    0.09
    ajo
    0.08
     Alo
    0.08
    çݰ代社ä¼ļ
    0.08
    æĿ¡ä»¶ä¸ĭ
    0.08
    Activations Density 0.054%

    No Known Activations