© 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. 55062
    Prev
    Next
    INDEX
    Explanations

    ounces or grams

    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
    dap
    -0.09
     Credits
    -0.08
    anders
    -0.08
    ä¸Ģ带
    -0.08
    ILON
    -0.08
    InView
    -0.08
    ÌĢ
    -0.08
    éķĸ
    -0.08
     Olympus
    -0.08
    ODO
    -0.08
    POSITIVE LOGITS
    åŃ£
    0.10
    è°ģèĥ½
    0.10
    ãģªãĤĬ
    0.09
    .pivot
    0.09
    heit
    0.09
    aque
    0.08
    æľīèĥ½åĬĽ
    0.08
    æ¾į
    0.08
    误åĮº
    0.08
    ulet
    0.08
    Activations Density 0.009%

    No Known Activations