© 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. 8001
    Prev
    Next
    INDEX
    Explanations

    office

    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
    æĭ¾
    -0.10
    ä¸įåı¯
    -0.10
    liable
    -0.09
    è¿ŀå¤ľ
    -0.09
    çĸ¤
    -0.09
    读åIJİ
    -0.09
    ä¸įåı¯ä»¥
    -0.09
    åįĬæľĪ
    -0.09
    æĸĩçī©ä¿ĿæĬ¤
    -0.09
    .Begin
    -0.09
    POSITIVE LOGITS
    åĬŀåħ¬
    0.20
    åĬŀåħ¬å®¤
    0.18
     office
    0.18
    åĬŀåħ¬æ¥¼
    0.15
     оÑĦиÑģ
    0.15
    Office
    0.14
    åĨĻåŃĹ楼
    0.14
    office
    0.14
    -office
    0.14
     Office
    0.13
    Activations Density 0.123%

    No Known Activations