© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36962
    Prev
    Next
    INDEX
    Explanations

    garments and styles of dress

    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
    èµģ
    -0.10
    olen
    -0.09
    è·µ
    -0.09
    leo
    -0.09
    足迹
    -0.09
    åĻ¨æĿIJ
    -0.08
    apg
    -0.08
    iad
    -0.08
    lea
    -0.08
    adera
    -0.08
    POSITIVE LOGITS
    è£ĻåŃIJ
    0.09
    å¼ı
    0.09
    æķŀå¼Ģ
    0.09
    è£Ļ
    0.09
    款å¼ı
    0.09
    åįķåĵģ
    0.09
    笳
    0.09
    æķŀ
    0.09
    çŁŃ
    0.08
    æľªæĪIJ
    0.08
    Activations Density 0.061%

    No Known Activations