© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17075
    Prev
    Next
    INDEX
    Explanations

    place names ending in ville

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    们
    -0.25
    ting
    -0.22
    ìĤ¬íķŃ
    -0.20
    ãĤ¥
    -0.20
    æľŁåĨħ
    -0.19
    lands
    -0.19
    ively
    -0.18
    ãĤ£
    -0.18
    äºĽ
    -0.17
    ../../../
    -0.17
    POSITIVE LOGITS
    aders
    0.20
    .ibm
    0.17
    edor
    0.17
    Soph
    0.17
    egment
    0.17
    eki
    0.16
    usa
    0.16
    Ùħا
    0.16
    .edu
    0.16
    ALES
    0.15
    Activations Density 0.021%

    No Known Activations