© 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. 3414
    Prev
    Next
    INDEX
    Explanations

    place names and geographical features

    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
    æ²®
    -0.10
    çķľçī§
    -0.09
    æµ·æĭĶ
    -0.09
    åħį
    -0.09
    äºĭåIJİ
    -0.09
    åĭº
    -0.09
    å´Ģ
    -0.09
    ä¸īåĨľ
    -0.09
    _EOL
    -0.09
    _PARTITION
    -0.09
    POSITIVE LOGITS
    å¸Ĥä¸Ńå¿ĥ
    0.10
    涤
    0.09
     downtown
    0.09
     Robbins
    0.09
    åľ¨ä¸Ĭæµ·
    0.09
    åŁİåĮº
    0.09
    ockey
    0.09
    åķĨåľĪ
    0.08
    GOR
    0.08
     city
    0.08
    Activations Density 0.443%

    No Known Activations