© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7997
    Prev
    Next
    INDEX
    Explanations

    book titles and media publication names

    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
    èļ±
    -0.11
    åŀĵ
    -0.10
    庵
    -0.09
    xon
    -0.09
    æľīä½ķ
    -0.09
     деÑıÑĤелÑĮ
    -0.09
    ork
    -0.09
    æĸ¹éĿ¢çļĦ
    -0.09
    羡
    -0.08
    解æĶ¾æĢĿæĥ³
    -0.08
    POSITIVE LOGITS
    ä¸ĢæīĢ
    0.08
    umbs
    0.08
    ä½ĨæĪij
    0.08
    è§Ħ模æľĢ大
    0.07
    å¤ļå°ij
    0.07
    indsight
    0.07
    ä½Ĩä»ĸ们
    0.07
     Gee
    0.07
    tur
    0.07
     Conf
    0.07
    Activations Density 0.126%

    No Known Activations