© 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. 3733
    Prev
    Next
    INDEX
    Explanations

    examination, documentation, identification

    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
    arez
    -0.09
    æł©
    -0.09
     sunk
    -0.08
    缸åºĶ
    -0.08
    zap
    -0.08
    å¯ĨéĽĨ
    -0.08
    æĶ¯
    -0.08
    ä¸įåĪĨ
    -0.08
    imension
    -0.08
    .caption
    -0.08
    POSITIVE LOGITS
    åľ¨çİ°åľº
    0.10
    è¯ģæį®
    0.10
    æľĭåıĭåľĪ
    0.09
    æĵ¦æĭŃ
    0.09
    æĻ¯å¾·
    0.09
    å·½
    0.09
    çī©
    0.09
    ä¸įéĶĪ
    0.08
    ÃľN
    0.08
     Dil
    0.08
    Activations Density 0.058%

    No Known Activations