© 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. 28105
    Prev
    Next
    INDEX
    Explanations

    attempt to

    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
    åĬŀäºĭ
    -0.10
    abouts
    -0.10
    enstein
    -0.09
    attention
    -0.09
    æŀķ
    -0.08
    zeitig
    -0.08
    èĥ½åĬĽåĴĮ
    -0.08
    çIJ°
    -0.08
    ç»Ĩç»Ĩ
    -0.08
     attention
    -0.08
    POSITIVE LOGITS
    å¹´ä¹ĭ
    0.11
    说çļĦæĺ¯
    0.10
    	TokenName
    0.10
    人éĢī
    0.10
    å¤ļç§įå½¢å¼ı
    0.10
    åĽĽèĤ¢
    0.09
    ively
    0.09
    ities
    0.09
    icl
    0.09
    Inlining
    0.08
    Activations Density 0.017%

    No Known Activations