© 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. 32024
    Prev
    Next
    INDEX
    Explanations

    also included or available

    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
    天涯
    -0.08
    åIJĦæĸ¹éĿ¢
    -0.08
     writ
    -0.08
    âĢ»
    -0.08
    éĤ£ä¸Ģ
    -0.07
     Singular
    -0.07
    çļĦæł·åŃIJ
    -0.07
     singular
    -0.07
     apart
    -0.07
    rement
    -0.07
    POSITIVE LOGITS
    æĺ¯æĪijçļĦ
    0.12
    egas
    0.11
    ä¹Łéĥ½
    0.10
    æĸŁ
    0.10
    æѤæ¡Ī
    0.09
    æѤ类
    0.09
    æ·ĭ
    0.09
    çĦī
    0.09
    ä¹Łæľī
    0.09
    å¼ĢåºĹ
    0.09
    Activations Density 0.330%

    No Known Activations