© 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. 49760
    Prev
    Next
    INDEX
    Explanations

    other + [noun]

    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
    éļ¶å±ŀ
    -0.10
    ses
    -0.09
    à¸Ĭà¸Ļ
    -0.09
    渣
    -0.09
    tm
    -0.09
    纵
    -0.09
    äºĨåIJĹ
    -0.08
    æľīå¾Īå¤ļç§į
    -0.08
    fort
    -0.08
    类似çļĦ
    -0.08
    POSITIVE LOGITS
    äºĭå®ľ
    0.09
    羣åĪĩ
    0.09
    éºĤ
    0.09
    æĸ¹éĿ¢
    0.09
    èļĢ
    0.08
    导åIJij
    0.08
    ARAM
    0.08
     INSTANCE
    0.08
    èĽĨ
    0.08
    åŁºæľ¬ä¿¡æģ¯
    0.08
    Activations Density 0.050%

    No Known Activations