© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52554
    Prev
    Next
    INDEX
    Explanations

    Chinatown, Italy, restaurant

    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¢Ĥ
    -0.10
    çĿĢä»ĸ
    -0.09
    顼
    -0.09
    ç°§
    -0.09
     toll
    -0.09
    TÃľ
    -0.08
     Embassy
    -0.08
    ä¹ĭåľ°
    -0.08
    æīįè¡Į
    -0.08
    å§Ĭ
    -0.08
    POSITIVE LOGITS
    ifornia
    0.10
    尽头
    0.09
    åħ¼
    0.09
    inky
    0.09
    å¿ĥå¢ĥ
    0.08
    æĮ½
    0.08
    è´§
    0.08
    ged
    0.08
    縱
    0.08
    IService
    0.08
    Activations Density 0.003%

    No Known Activations