© 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. 2831
    Prev
    Next
    INDEX
    Explanations

    Cyrillic and non-Latin characters

    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
    ervo
    -0.11
    istic
    -0.10
    å¬ĸ
    -0.09
    IMS
    -0.09
    asis
    -0.09
    æĪij以为
    -0.09
    ç«Łæĺ¯
    -0.08
    ÑijÑĢ
    -0.08
    BED
    -0.08
    ä»ĸ们éĥ½
    -0.08
    POSITIVE LOGITS
    -vous
    0.12
     Majesty
    0.09
    楼ä¸ĭ
    0.09
    æĤ¨çļĦ
    0.09
    \core
    0.09
    çİĸ
    0.09
    hare
    0.09
    åºł
    0.08
    æĤ¨
    0.08
    burger
    0.08
    Activations Density 0.037%

    No Known Activations