© 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. 35887
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

    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
    æīįè¡Į
    -0.09
    ä¸įæĩĪ
    -0.08
    åİĮ
    -0.08
    ç®Ģ缴
    -0.08
    æįĨç»ij
    -0.08
    dag
    -0.07
    å¹²èĦĨ
    -0.07
    å·²ç»ıæľīäºĨ
    -0.07
    æŃ£åľ¨è¿Ľè¡Į
    -0.07
    OLS
    -0.07
    POSITIVE LOGITS
    ç»ĵå±Ģ
    0.14
    æķĻè®Ń
    0.13
    èĩ³ä»Ĭ
    0.12
     lesson
    0.12
    第äºĮ天
    0.12
    èĩ³æѤ
    0.11
    æѤåIJİ
    0.11
    åIJİæĿ¥
    0.11
    èĩªæѤ
    0.11
    lesson
    0.10
    Activations Density 0.085%

    No Known Activations