© 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. 48572
    Prev
    Next
    INDEX
    Explanations

    lottery, lotto, lot, lotta

    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
    ness
    -0.10
    /page
    -0.09
    çĶ¸
    -0.09
    ley
    -0.08
    клад
    -0.08
    liest
    -0.08
    ément
    -0.08
    ÙĪÙĩ
    -0.08
    主æĦı
    -0.08
    finder
    -0.08
    POSITIVE LOGITS
    สà¸Ķ
    0.10
    ALLY
    0.10
    æĪIJè´¥
    0.09
    eer
    0.09
    å¾Ĵ
    0.09
    Slim
    0.09
    ç»ĵæĿŁåIJİ
    0.09
    lan
    0.09
    æĢ§å¼º
    0.09
    çĽį
    0.08
    Activations Density 0.002%

    No Known Activations