© 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. 3847
    Prev
    Next
    INDEX
    Explanations

    wine regions or places

    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
    éĹ³
    -0.12
    çĨĬçĮ«
    -0.09
    iph
    -0.09
     Hoe
    -0.09
     ASN
    -0.08
     phạm
    -0.08
    æľį
    -0.08
    åĨ»ç»ĵ
    -0.08
    affles
    -0.08
    è¿ĶåĽŀ
    -0.08
    POSITIVE LOGITS
    产åĮº
    0.10
    é£İåħī
    0.09
    ä½İ端
    0.09
    æľĢ好çļĦ
    0.09
    建ç«ĭäºĨ
    0.08
    åĪĨå±Ģ
    0.08
    宣è¨Ģ
    0.08
    Beth
    0.08
    alan
    0.08
    Region
    0.08
    Activations Density 0.035%

    No Known Activations