© 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. 36510
    Prev
    Next
    INDEX
    Explanations

    business and customers

    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
    ä¸Ń级
    -0.10
    åľ¨åħ¨çIJĥ
    -0.10
    讽åĪº
    -0.10
    éŨæĪ·ç½ijç«Ļ
    -0.09
    pus
    -0.09
    åºŃéĻ¢
    -0.09
     PROCUREMENT
    -0.09
     highways
    -0.09
    lickr
    -0.09
    _ANT
    -0.09
    POSITIVE LOGITS
    顾客
    0.16
    åijĺå·¥
    0.14
    ç»ıèIJ¥
    0.14
    åºĹåĨħ
    0.13
    å¼Ģä¸ļ
    0.13
    ç»ıèIJ¥èĢħ
    0.12
    èIJ¥è¿IJ
    0.12
    ç¶ĵçĩŁ
    0.12
    ç»ıèIJ¥æ¨¡å¼ı
    0.12
    èĢģæĿ¿
    0.11
    Activations Density 0.138%

    No Known Activations