© 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. 2196
    Prev
    Next
    INDEX
    Explanations

    children and offspring

    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
     Gone
    -0.09
    æĢ§çļĦ
    -0.09
    æ£ļ
    -0.09
    æĪIJ年人
    -0.09
    eous
    -0.08
    enville
    -0.08
    大åĬĽ
    -0.08
    æĪIJçĨŁçļĦ
    -0.08
     ine
    -0.08
    æĬĬèĩªå·±çļĦ
    -0.08
    POSITIVE LOGITS
    æ±ľ
    0.11
    ãģ¡ãĤĥãĤĵ
    0.09
    å°ijçĪ·
    0.09
    .Builder
    0.08
    ä½ij
    0.08
    æĪijæīį
    0.08
    eman
    0.08
    ichert
    0.08
    æģĭ人
    0.08
    tring
    0.08
    Activations Density 0.075%

    No Known Activations