© 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. 10168
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    å°½
    -0.10
    ç»Ļèĩªå·±
    -0.10
    个æĢ§
    -0.10
    群
    -0.09
    ç«ŀ
    -0.09
    群éĩĮ
    -0.09
    ARI
    -0.09
    汶
    -0.09
    æŀķ
    -0.08
    çĽ¡
    -0.08
    POSITIVE LOGITS
    è®Ńç»ĥ
    0.12
    åŁ¹è®Ń
    0.11
     training
    0.11
     Training
    0.11
    å¥ĸåĬ±
    0.10
    training
    0.10
     trainer
    0.10
    Training
    0.10
    饵
    0.10
    trainer
    0.10
    Activations Density 0.076%

    No Known Activations