© 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. 7935
    Prev
    Next
    INDEX
    Explanations

    text enclosed in quotation marks

    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
    è¡·
    -0.09
    ÑĢак
    -0.09
    æĭ®
    -0.09
    èĨĽ
    -0.09
    strand
    -0.08
    å°´å°¬
    -0.08
    èĽ¹
    -0.08
    家人
    -0.08
    è¡°
    -0.08
    èī²ç´ł
    -0.08
    POSITIVE LOGITS
    ãĢģ“
    0.09
     (?)
    0.09
    innie
    0.09
    ä¹Łå°±æĺ¯
    0.09
     circular
    0.09
    erd
    0.09
    ä¼¼çļĦ
    0.08
    olon
    0.08
    alley
    0.08
    没æľīæĥ³åĪ°
    0.08
    Activations Density 0.126%

    No Known Activations