© 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. 30659
    Prev
    Next
    INDEX
    Explanations

    biblical stories and 'uria' announcements

    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
    绥
    -0.09
    .uml
    -0.08
    aille
    -0.08
    losion
    -0.08
    aisy
    -0.08
    idge
    -0.08
    åIJĦçľģ
    -0.08
    è¿ľ
    -0.08
    èIJ½å®ŀ
    -0.08
     Cater
    -0.07
    POSITIVE LOGITS
    æ²¥
    0.10
    åĹĦ
    0.10
    ä¸Ń举
    0.09
    æĸĩæľ¬
    0.09
    ackers
    0.09
    绾
    0.09
    洪水
    0.09
    ä¸Ĭå¸Ŀ
    0.09
    rig
    0.09
    河水
    0.08
    Activations Density 0.082%

    No Known Activations