© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20136
    Prev
    Next
    INDEX
    Explanations

    enjoy watch relax

    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
    oted
    -0.09
    ä¿Ĺ
    -0.09
    饰
    -0.09
    edith
    -0.09
    gles
    -0.09
    ä»Ķ
    -0.09
     khá»ķ
    -0.08
    箪
    -0.08
    èł¢
    -0.08
    icter
    -0.08
    POSITIVE LOGITS
    craft
    0.10
    å°¼äºļ
    0.10
    æĦŁåĬ¨
    0.09
    éģIJ
    0.09
     Crafts
    0.09
    æĥĬåĸľ
    0.09
    /manual
    0.09
    çľī
    0.09
    é©ļ
    0.08
    åĽŀåij³
    0.08
    Activations Density 0.016%

    No Known Activations