© 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. 2559
    Prev
    Next
    INDEX
    Explanations

    london based

    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
    们
    -0.11
    ÑģÑı
    -0.10
    ments
    -0.10
    æľ¬äºº
    -0.09
    oons
    -0.09
    een
    -0.09
    ä»ĬçĶŁ
    -0.09
    èĩ³äºİ
    -0.09
    天ä¸ĭ
    -0.09
    é¢Ŀ度
    -0.09
    POSITIVE LOGITS
    izer
    0.13
     lẽ
    0.10
    IZER
    0.10
    sworth
    0.10
    ization
    0.10
    istas
    0.10
    ised
    0.10
    ale
    0.09
    åIJĦåĮº
    0.09
    ä¹ĭæĺŁ
    0.09
    Activations Density 0.017%

    No Known Activations