© 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. 31828
    Prev
    Next
    INDEX
    Explanations

    prediction and forecasts

    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
    æĶ¶æĶ¯
    -0.12
    ĺ认
    -0.10
    зван
    -0.09
    åŃIJ女
    -0.09
    ä¸ĩ象
    -0.09
    寻æ±Ĥ
    -0.09
    èģĺ
    -0.09
    ç¹ģ
    -0.09
    å¾ģæ±Ĥ
    -0.09
    åѦä½į
    -0.09
    POSITIVE LOGITS
    é¢Ħè¨Ģ
    0.20
    é¢Ħè§ģ
    0.17
    é¢Ħæµĭ
    0.16
    é¢ĦèѦ
    0.15
    æıIJåīį
    0.13
     predictions
    0.12
    é¢ĦæĬ¥
    0.12
     prediction
    0.12
     Prediction
    0.11
    è°¶
    0.11
    Activations Density 0.064%

    No Known Activations