© 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. 9126
    Prev
    Next
    INDEX
    Explanations

    military wife and accommodation

    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
    åĨĬ
    -0.11
    æŀ¶
    -0.11
    çŃĸ
    -0.10
    åķ¬
    -0.10
    èĭ£
    -0.09
     broker
    -0.09
    lop
    -0.09
     sod
    -0.09
    ÑĨип
    -0.08
    Lov
    -0.08
    POSITIVE LOGITS
    妻
    0.11
    移
    0.11
    俱ä¹IJ
    0.10
    ç²Ĺ
    0.10
    åŃIJ女
    0.09
    èģĮå·¥
    0.09
    çĶŁæ´»åľ¨
    0.09
    çľ·
    0.09
    éĻĦå±ŀ
    0.09
    æ¤ħ
    0.09
    Activations Density 0.137%

    No Known Activations