© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1240
    Prev
    Next
    INDEX
    Explanations

    guinea pigs, pet, rats, hamster

    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
    _DL
    -0.11
    é©¿
    -0.10
    éĢ¼
    -0.09
    æľī个
    -0.09
    æĭĶ
    -0.09
    éĢļçĶ¨
    -0.09
    åģľè½¦
    -0.09
    æĪĹ
    -0.09
    Netflix
    -0.09
    åįıè°ĥåıijå±ķ
    -0.09
    POSITIVE LOGITS
    è¨Ģ论
    0.09
    åķ®
    0.09
    =model
    0.09
     phá»iji
    0.09
    è²Ĥ
    0.09
    ä¸įåIJĥ
    0.08
    饲åħ»
    0.08
    ç»ŀ
    0.08
    æĪ¡
    0.08
    èĥ¥
    0.08
    Activations Density 0.105%

    No Known Activations