© 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. 52055
    Prev
    Next
    INDEX
    Explanations

    Republicans

    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
    ä¾ĽéľĢ
    -0.11
    åIJĦæł·
    -0.10
    ä¸Ńåħ±
    -0.09
    庶
    -0.09
    å¸ĪäºĭåĬ¡æīĢ
    -0.09
    èĢģ人家
    -0.09
    å¬ĸ
    -0.09
    -0.09
    举æŃ¢
    -0.09
    èĢĥä¸Ĭ
    -0.08
    POSITIVE LOGITS
    ../../../../
    0.09
    aska
    0.09
    innen
    0.08
    nen
    0.08
    ../../../
    0.08
    usable
    0.08
    ä¸Ģæĸ¹
    0.08
    iano
    0.08
    nex
    0.08
    å¨ħ
    0.08
    Activations Density 0.014%

    No Known Activations