© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51890
    Prev
    Next
    INDEX
    Explanations

    place names often ending in 'ton' or 'minster'

    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
    èį·
    -0.09
    æŃ¥éª¤
    -0.09
     steps
    -0.08
    åIJĦæĸ¹éĿ¢
    -0.08
    å±Ī
    -0.08
    éĥ¨åĪĨ
    -0.08
    uhan
    -0.08
     Canter
    -0.08
    å°±è¦ģ
    -0.07
    å°±åºĶ该
    -0.07
    POSITIVE LOGITS
    æ¦ľ
    0.10
    æľºåĬ¨
    0.10
    hma
    0.09
    æĪij对
    0.09
     depreci
    0.09
    иÑĩеÑģ
    0.09
    apes
    0.09
    .Cursors
    0.09
    й
    0.09
    表æī¬
    0.08
    Activations Density 0.191%

    No Known Activations