© 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. 61764
    Prev
    Next
    INDEX
    Explanations

    Norwegian/Danish words and names

    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
    ed
    -0.09
    大åĨĽ
    -0.09
    ách
    -0.09
    ä¸Ģéĺµ
    -0.08
    çļĦæĸ¹å¼ı
    -0.08
    lings
    -0.08
    çļĦå°±æĺ¯
    -0.08
    çļĦè¿ĩç¨ĭ
    -0.08
    ä¸Ģ段æŶéĹ´
    -0.08
    tons
    -0.08
    POSITIVE LOGITS
    zelf
    0.14
    ivery
    0.10
    uden
    0.10
    ги
    0.10
    oretical
    0.10
    illin
    0.10
    æĹ¢çĦ¶
    0.09
    æīģ
    0.09
    _APPLICATION
    0.09
    uzzi
    0.09
    Activations Density 0.044%

    No Known Activations