© 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. 30847
    Prev
    Next
    INDEX
    Explanations

    sacred sites, traditional ceremony, knowledge learning, Recipes

    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
    éĢļçĶ¨
    -0.10
    ëį°
    -0.10
    åIJĮæĥħ
    -0.10
    èĪĮ头
    -0.09
    illon
    -0.09
    .serialize
    -0.09
    èĪ«
    -0.09
    è¯İ
    -0.09
    åºĬä½į
    -0.09
    便åĪ©
    -0.09
    POSITIVE LOGITS
    ç»Ŀä¸į
    0.09
     unw
    0.09
    amy
    0.08
    หาย
    0.08
    æĻ°
    0.08
    湫
    0.08
    ale
    0.08
    eg
    0.08
    atures
    0.08
     Walter
    0.08
    Activations Density 0.066%

    No Known Activations