© 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. 52167
    Prev
    Next
    INDEX
    Explanations

    Opry, Research, Licensed, story, known

    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
    é»ijçĻ½
    -0.09
    دÙĨ
    -0.09
    illus
    -0.09
     Porter
    -0.08
     Babe
    -0.08
    aten
    -0.08
    æĭĸ
    -0.08
     Helm
    -0.08
    羣å®ŀçļĦ
    -0.08
    å±ıéļľ
    -0.08
    POSITIVE LOGITS
    ÑĥÑĢ
    0.09
    å©¿
    0.09
    ney
    0.09
    æİ¥åĬĽ
    0.09
    åıĮåIJij
    0.09
    brook
    0.09
    åĬŀäºĭ
    0.09
    knife
    0.08
    åħ¨çIJĥæľĢ大
    0.08
    è°¯
    0.08
    Activations Density 0.001%

    No Known Activations