© 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. 23408
    Prev
    Next
    INDEX
    Explanations

    European continent languages

    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
    èĬĿ麻
    -0.10
    ainter
    -0.10
    åĨľæĿij
    -0.09
    gov
    -0.09
    鸾
    -0.09
    ä¸ĸçķĮè§Ĥ
    -0.09
    央
    -0.09
    åĪ¤
    -0.08
    éĢĨè¡Į
    -0.08
    æĿijéĩĮ
    -0.08
    POSITIVE LOGITS
     European
    0.10
    åħ¶ä»ĸåĽ½å®¶
    0.10
    æĭīä¸ģ
    0.10
    欧洲
    0.10
     Latin
    0.09
    æĦı大åĪ©
    0.09
     Sle
    0.09
    -European
    0.09
    èĢĥå¯Ł
    0.09
     xứ
    0.09
    Activations Density 0.092%

    No Known Activations