© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37187
    Prev
    Next
    INDEX
    Explanations

    domains like .io, .com, .me

    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
    åŁĭ
    -0.09
    ä¼ĺè´¨
    -0.08
    éĽķ
    -0.08
    wan
    -0.08
    æ¤įåħ¥
    -0.08
    è£ħä¿®
    -0.08
    æģķ
    -0.08
    หย
    -0.08
    å¾Ĺ天
    -0.08
    .ends
    -0.08
    POSITIVE LOGITS
    妪
    0.09
    éľģ
    0.09
    çļĦæĦıä¹ī
    0.09
    asma
    0.09
    缨
    0.08
    Parms
    0.08
    éĴ¢æĿ¿
    0.08
    DEV
    0.08
    UTO
    0.08
    모
    0.08
    Activations Density 0.020%

    No Known Activations