© 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. 20674
    Prev
    Next
    INDEX
    Explanations

    Shop, medieval, century, origin

    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
    å¤į
    -0.11
    å¾ľ
    -0.10
     пÑĢоÑĩ
    -0.09
    semi
    -0.09
    èŀ¯
    -0.09
    夫
    -0.09
    復
    -0.09
    å¯ĵ
    -0.09
    æ¯ķ
    -0.09
    ramer
    -0.09
    POSITIVE LOGITS
    -Control
    0.10
    çĶµæ¢¯
    0.09
    èĭ¦
    0.09
    ç²Ł
    0.09
    çĺģ
    0.09
    åįİåĮĹ
    0.09
    om
    0.09
     Kid
    0.08
    梢
    0.08
    undef
    0.08
    Activations Density 0.096%

    No Known Activations