© 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. 8184
    Prev
    Next
    INDEX
    Explanations

    oath, pledge, sworn in

    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
    åħ³éŨ
    -0.11
    èĴ¸
    -0.10
    缴éĢļ车
    -0.09
    妲
    -0.09
    åī¥
    -0.09
    èľ©
    -0.09
    媳å¦ĩ
    -0.09
    åĸľ
    -0.09
    ä¹ĭ家
    -0.09
    uru
    -0.09
    POSITIVE LOGITS
    èªĵ
    0.13
    å¿łè¯ļ
    0.13
     oath
    0.12
    å¿ł
    0.11
    èªĵè¨Ģ
    0.11
     allegiance
    0.11
    loy
    0.10
    é»ĺ
    0.10
    æī¿è¯º
    0.10
    pled
    0.10
    Activations Density 0.027%

    No Known Activations