© 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. 56622
    Prev
    Next
    INDEX
    Explanations

    buying or purchasing assets

    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
    è¿Ń
    -0.09
    _extraction
    -0.09
    èĤĮèĤī
    -0.09
    alto
    -0.08
    æīĭèħķ
    -0.08
    born
    -0.08
    èıĬ
    -0.08
    éĤ¦
    -0.08
    åIJijå¤ĸ
    -0.08
    builders
    -0.08
    POSITIVE LOGITS
    æ¤Ł
    0.15
    èµİ
    0.10
     groceries
    0.09
    è¯ģ
    0.09
    è¿ĻæĶ¯
    0.09
    æĢ»ä»·
    0.09
    ä¹°çļĦ
    0.09
    å¿ĥ仪çļĦ
    0.09
    è´Ńä¹°
    0.09
    æķĻè®Ń
    0.09
    Activations Density 0.067%

    No Known Activations