© 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. 26449
    Prev
    Next
    INDEX
    Explanations

    Asian community and awards

    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
    å¹´è½»çļĦ
    -0.09
    éĹ®æĪij
    -0.09
    å°»
    -0.09
    å¤ĩ
    -0.09
    好转
    -0.09
    mate
    -0.09
    çľ¼æ³ª
    -0.09
    女ãģ®
    -0.08
    åı¯èĥ½åıijçĶŁ
    -0.08
    èĢĮä¸įæĺ¯
    -0.08
    POSITIVE LOGITS
    é¹Ĭ
    0.10
    奥æĸ¯åį¡
    0.09
    é«ĺ管
    0.09
     Oscar
    0.09
    èĩªæĿ¥
    0.09
    主æµģ
    0.08
    opus
    0.08
    ACHI
    0.08
    åıĤ
    0.08
    æĽĻåħī
    0.08
    Activations Density 0.123%

    No Known Activations