© 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. 53984
    Prev
    Next
    INDEX
    Explanations

    code and files

    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
    ?url
    -0.09
    çĻ¾å¹´
    -0.09
    паÑģ
    -0.08
    廨
    -0.08
     Hạ
    -0.08
    ëıĮ
    -0.08
     sæ
    -0.08
     ÑĤе
    -0.08
     dolayı
    -0.08
    ÑģÑĤеÑĢ
    -0.08
    POSITIVE LOGITS
    åĪĨæĺİ
    0.10
    åIJĦèĩª
    0.10
    åħ·ä½ĵ
    0.10
    ä¸įåIJĮç¨ĭ度
    0.09
    åĨĻä½ľ
    0.09
    åIJĦæľī
    0.09
    éĨĴ
    0.09
    寸
    0.09
    æ±Ĺ
    0.09
    ç¨Ģ
    0.09
    Activations Density 0.060%

    No Known Activations