© 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. 3005
    Prev
    Next
    INDEX
    Explanations

    Roman law or philosophy

    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
    头çĸ¼
    -0.10
    è¶Ł
    -0.09
    嵩
    -0.09
    æĪIJåĵģ
    -0.09
    è½
    -0.09
    头çĹĽ
    -0.09
    å¼Ģæľº
    -0.09
    é¢IJ
    -0.08
    hoot
    -0.08
    åłĤ
    -0.08
    POSITIVE LOGITS
    å¥łåŁº
    0.11
    ä¿Ŀ驾
    0.10
    æ²»çIJĨ
    0.09
    .arc
    0.09
    åĩĢåĮĸ
    0.09
    essay
    0.09
     tracing
    0.09
     Butler
    0.09
    èIJ½æĪ·
    0.09
    篡
    0.08
    Activations Density 0.077%

    No Known Activations