© 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. 47804
    Prev
    Next
    INDEX
    Explanations

    anti-poverty tool

    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
    çıŃåŃIJ
    -0.10
    麻
    -0.10
    ä¸įåĨį
    -0.09
    ä¹ŁåºĶ该
    -0.09
    说è¯Ŀ
    -0.09
    å½ĵçĦ¶æĺ¯
    -0.09
    轸
    -0.09
    ddy
    -0.09
    ä¸įåºĶ该
    -0.09
    å®īåİ¿
    -0.09
    POSITIVE LOGITS
    羣æŃ£
    0.13
    å®ŀéĻħä¸Ĭ
    0.12
    并ä¸įèĥ½
    0.12
    æĽ´å¤ļçļĦæĺ¯
    0.11
    è¿ĺä¸įå¦Ĥ
    0.11
    å¾Ĵ
    0.11
    å®ŀéĻħä¸Ĭæĺ¯
    0.11
    實éļĽ
    0.11
    å®ŀéĻħ
    0.10
    åıįèĢĮ
    0.10
    Activations Density 0.110%

    No Known Activations