© 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. 52056
    Prev
    Next
    INDEX
    Explanations

    annexation, war, history, Persia

    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
    çģ¼
    -0.09
    åĮĹæĸĹ
    -0.09
    çļĦä¿¡å¿ĥ
    -0.09
    ãģ©ãĤĵãģ©
    -0.08
    éħįåģ¶
    -0.08
    ynamo
    -0.08
    åĪijèѦ
    -0.08
    è½²
    -0.08
    ä¸ĵçĶ¨
    -0.08
    ç¢ĵ
    -0.08
    POSITIVE LOGITS
    èĹ©
    0.10
    è¾ľ
    0.09
    è§IJ
    0.08
    è´¡
    0.08
    ioni
    0.08
    é¢Ĩ导ä¸ĭ
    0.08
    é¢Ĩ导
    0.08
     REF
    0.08
    èĮ¬
    0.08
    TEX
    0.08
    Activations Density 0.077%

    No Known Activations