© 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. 22414
    Prev
    Next
    INDEX
    Explanations

    onset of

    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
    顺德
    -0.09
    æĮģèĤ¡
    -0.08
    è¿Ļæĸ¹éĿ¢
    -0.08
    åĴĮçĿ¦
    -0.08
    èĤ¡
    -0.08
    ä¹ĭåīįçļĦ
    -0.08
    ç§ĥ
    -0.08
     Kg
    -0.07
    å®Į
    -0.07
    ç½ij讯
    -0.07
    POSITIVE LOGITS
    cies
    0.09
    褶
    0.09
    é¢Ĩçķ¥
    0.09
    à¸ģรรม
    0.09
    æijĨ
    0.09
    æĪ¿æºIJ
    0.09
    è¥
    0.08
    éłĺ
    0.08
    蹩
    0.08
    steen
    0.08
    Activations Density 0.303%

    No Known Activations