© 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. 10638
    Prev
    Next
    INDEX
    Explanations

    country names and places

    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
    ä¸Ĭåīį
    -0.09
    禽
    -0.09
    æĺ¯ä¸ĢåIJį
    -0.09
    éĢĹ
    -0.09
     Appalach
    -0.09
    Ware
    -0.09
     Appalachian
    -0.09
    uckles
    -0.08
    åĶ®ç¥¨
    -0.08
    诫
    -0.08
    POSITIVE LOGITS
    迪æĭľ
    0.11
    çİĭåĽ½
    0.10
    æĭĨ
    0.10
    tiny
    0.10
    å¢ĥçķĮ
    0.10
    éħĭ
    0.10
    æĪIJåijĺåĽ½
    0.09
     tiny
    0.09
    å¾®åŀĭ
    0.09
    åħ¶ä»ĸåĽ½å®¶
    0.09
    Activations Density 0.181%

    No Known Activations