© 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. 9200
    Prev
    Next
    INDEX
    Explanations

    old actor or literature

    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
     tons
    -0.09
    ìŀ¥ìĿĦ
    -0.09
    пÑĥÑģка
    -0.09
    æį»
    -0.09
    æĭĪ
    -0.09
    ложениÑı
    -0.09
    é¢ł
    -0.09
    ymes
    -0.09
    èijº
    -0.09
    åĴĮå°ļ
    -0.09
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.09
    нÑĥ
    0.08
    è¿ĺå¾Ĺ
    0.08
     Bergen
    0.07
     proprietary
    0.07
    elle
    0.07
    éĹŃ
    0.07
    IRO
    0.07
    (pp
    0.07
    ouse
    0.07
    Activations Density 0.991%

    No Known Activations