© 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. 2686
    Prev
    Next
    INDEX
    Explanations

    place names and institutions

    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
    éĵ¡
    -0.10
    çļĩ
    -0.09
    Frozen
    -0.09
    秧
    -0.09
    ç»Ĵ
    -0.09
     Louisville
    -0.09
    æµ·æ°´
    -0.09
    ittal
    -0.09
     dÆ°Æ¡ng
    -0.08
    usta
    -0.08
    POSITIVE LOGITS
    PTY
    0.09
     Maharashtra
    0.09
     Worcester
    0.09
    çIJ¥
    0.09
    åįİ举
    0.09
    æĹłéĶ¡
    0.09
    çķħéĢļ
    0.09
    å¨ĵ
    0.09
     Essex
    0.09
    èµĦ
    0.09
    Activations Density 0.188%

    No Known Activations