© 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. 8625
    Prev
    Next
    INDEX
    Explanations

    all-time records or favorites

    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
    lah
    -0.09
     جدا
    -0.09
    èĢģé¾ĦåĮĸ
    -0.09
    ä»Ģä¹Īæł·
    -0.09
    ibli
    -0.09
    ãģ³
    -0.09
    PRI
    -0.08
    usta
    -0.08
    缸åĬ©
    -0.08
    quete
    -0.08
    POSITIVE LOGITS
    æľĢçĪ±
    0.10
     classics
    0.09
    ìłģìľ¼ë¡ľ
    0.09
    leck
    0.08
    ç³Ł
    0.08
    ense
    0.08
    ython
    0.08
    IgnoreCase
    0.08
    åħħ
    0.08
    ä¸Ģä¸Ģ
    0.08
    Activations Density 0.003%

    No Known Activations