© 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. 18979
    Prev
    Next
    INDEX
    Explanations

    amphibia, amphitheatre, amphipathic

    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
    ìĤ¬íķŃ
    -0.10
    å®
    -0.10
    åĬĽè¿ĺæĺ¯
    -0.09
    éĺĹ
    -0.09
    ãģıãĤĮ
    -0.09
    çĭIJ
    -0.09
    estroy
    -0.09
    æĢ§
    -0.09
    èĵĬ
    -0.08
    utan
    -0.08
    POSITIVE LOGITS
    ÑĩаÑĤ
    0.10
    .bulk
    0.10
    失信
    0.10
    åĨħçļĦ
    0.09
    æ¥Ķ
    0.09
    éī´
    0.09
     giác
    0.09
    å¡ŀ
    0.09
    ÑĦа
    0.08
     ÑĦигÑĥÑĢ
    0.08
    Activations Density 0.004%

    No Known Activations