© 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. 4759
    Prev
    Next
    INDEX
    Explanations

    main function or entry point

    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
    å¤įå·¥
    -0.08
    èѬå¦Ĥ
    -0.08
    飧æĢ§
    -0.08
     --
    -0.07
    Via
    -0.07
    磨
    -0.07
    åīįä¸ĸ
    -0.07
    lio
    -0.07
     markup
    -0.07
    isci
    -0.07
    POSITIVE LOGITS
    .mainloop
    0.11
    main
    0.11
    MAIN
    0.10
    .Main
    0.10
    (main
    0.10
    .usage
    0.09
    nesc
    0.09
     main
    0.09
    Öģ
    0.09
    otate
    0.09
    Activations Density 0.718%

    No Known Activations