© 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. 58119
    Prev
    Next
    INDEX
    Explanations

    completely

    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
    æ®Ĭ
    -0.10
    hap
    -0.09
    à¸Ħà¸Ńย
    -0.09
    illi
    -0.09
    广大群ä¼Ĺ
    -0.09
    .gstatic
    -0.08
    æģķ
    -0.08
    autoload
    -0.08
    ä¿Ŀ管
    -0.08
    Spi
    -0.08
    POSITIVE LOGITS
    å½»åºķ
    0.12
    enger
    0.10
    æ¢Ń
    0.10
    æij©
    0.09
    æĦıæĢĿæĺ¯
    0.09
    解æĶ¾
    0.09
    å½»
    0.09
    å¾¹
    0.09
    ans
    0.09
    зам
    0.09
    Activations Density 0.030%

    No Known Activations